plugins/gitea/agents/gitea-orchestrate.md and .agent.md were fully
written but the plugin manifest never declared an "agents" key, so
the plugin loader had no path to discover/register the agent (unlike
plugins/git and plugins/kyberforge, which both declare "agents":
"agents/"). Bump the patch version in both manifests per plugin-author's
UPDATE flow convention, since consumers cache plugin metadata by version.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VwtxcDXuLZxYzWnT2FaoZU
A documentation-accuracy audit against research docs found three gotchas
in troubleshooting.md that were dropped from gitea-files/SKILL.md during
original authoring: signed-commit branch protection silently blocking
file writes (a distinct failure mode from stale-SHA that an agent could
otherwise misdiagnose and retry indefinitely), reverse-proxy 413s on
large base64-encoded write payloads, and 404-vs-403 scope masking on the
read tools. Also adds the context7-gitea-tea-cli provenance entry to
references/sources.md (Contributing files: none) to resolve a
pre-existing skill-audit provenance FAIL surfaced while validating this
change, matching the pattern already used by sibling skills.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VwtxcDXuLZxYzWnT2FaoZU
A documentation-accuracy audit against plugins/gitea/docs/research/docs/gitea/*.md
found three overclaims/unsupported claims in skill content:
- gitea-labels-milestones: reworded the exclusive-flag gotcha and
label-inference.md's "scoped labels" section — exclusive is documented as
org-labels-only (api-reference.md, data-model.md) and unsupported by the
live create_repo_label/edit_repo_label schema, so repo-level exclusivity
for Kind/*/Priority/*/Status/* is a client-side convention this skill
enforces via replace_labels, not a server guarantee.
- gitea-labels-milestones: added a "Step 1 — Resolve owner and repo" section
(git remote get-url origin) and Bash to allowed-tools, since
milestone_read/milestone_write and repo-scoped label_read/label_write
hard-require owner+repo and the skill is documented as directly invokable,
matching the pattern already in gitea-issues/SKILL.md.
- gitea-issues: softened the claim that Gitea parses Fixes #N/Closes #N in
commit messages to auto-close issues — no research doc supports this, and
examples.md states issues are not auto-closed on PR merge. Now notes the
behavior is plausible but unconfirmed, keeping the issue_read re-check.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VwtxcDXuLZxYzWnT2FaoZU
An audit against plugins/gitea/docs/research/docs/gitea/*.md found the
gitea-releases skill told callers to set create_release's draft flag
as `draft` instead of `is_draft` (the actual input param; `draft` is
only the response field name) - a call following that gotcha would
have the flag silently ignored, publishing a non-draft release.
Also corrected an overclaimed "verified against live MCP schema"
provenance note in call-signatures.md/README.md (its sources are
gitea-mcp source-code extraction, not a live tool call - now noted
alongside a narrow live ToolSearch cross-check performed this session
for 3 of the 9 tools' input params), and softened three behavioral
claims (create_release auto-creating tags, get_latest_release
excluding drafts/prereleases, delete_tag preserving a wrapping
release) that don't trace to any research doc, with a recommendation
to verify release/tag state after delete operations rather than
assume it.
Adds the deterministic, agent-facing counterpart to gitea-workflow per
docs/adr/0011-gitea-skill-deep-modules.md, mirroring git-orchestrate's
shape: structured request/response JSON, safety gates on destructive
ops (delete-branch/release/tag/label/milestone/file, merge-pr), and
routing across the six gitea domain skills without conversational
disambiguation. Authored via kyberforge:agent-author directly (not
forge) since the artifact type was already known, and validated clean
via kyberforge:agent-audit (structure, provenance, and qualitative
checks all pass). Bumps plugin version 1.2.0 -> 1.3.0 in both manifests.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
Adds the human-facing entry point and dispatcher for the Gitea
integration per docs/adr/0011-gitea-skill-deep-modules.md. Preserves
the retired flat skill's default no-args status view (open issues +
open PRs, composed via list_issues/list_pull_requests) and extends
its dispatch table to route ambiguous requests across all 6 domain
skills (issues, labels/milestones, prs, branches, files, releases) —
the old table only covered 4 of these. The skill only calls
gitea-mcp tools directly for the composed status view; every other
operation is a routed handoff to the owning sibling skill, keeping
execution logic (call signatures, gotchas, confirmation gates) owned
in one place.
Bumps plugins/gitea version 1.1.0 -> 1.2.0 in both manifests for the
new skill. Passed structural validation, provenance validation, and
an independent clean-context skill-audit recheck (one finding fixed:
allowed-tools was missing the Skill tool needed for routing).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
Adds the human-facing entry point and router for the Gitea integration,
replacing the old flat /gitea skill per ADR 0011. It composes the six
domain skills (gitea-issues, gitea-labels-milestones, gitea-prs,
gitea-branches, gitea-files, gitea-releases) rather than calling any
Gitea MCP tool directly, mirroring git-workflow's router shape.
Preserves the old flat skill's default no-args status view (open
issues + open PRs, two sections) and adds deterministic ambiguous
issue-vs-PR number resolution via issue_read's is_pull field, since
issues and PRs share one number space in Gitea.
Authored via kyberforge:forge -> skill-author, with an independent
clean-context skill-audit re-run confirming no findings.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
An independent clean-context audit of the newly-authored gitea-prs skill
flagged that old_line_num/new_line_num (write path, pull_request_review_write
create) and position/old_position (read path, get_review_comments) name the
same concept differently — the same class of write/read field mismatch that
produced the review_scomments typo elsewhere in this domain. Adds one
clarifying sentence to references/reviews.md so an agent skimming only one
side doesn't assume symmetric field names.
Covers list_pull_requests, pull_request_read, pull_request_write, and
pull_request_review_write, split out of the flat plugins/bin/skills/gitea
PR-dispatch logic per ADR 0011. Composes gitea-labels-milestones for
label/milestone ID resolution instead of duplicating that lookup.
Tool signatures were cross-checked live via ToolSearch against the deployed
gitea-mcp server rather than copied from api-reference.md, per the ADR's
schema-drift mitigation process.
Covers list_issues, issue_read, issue_write, and search_issues, closing out
all four enrichments deferred from issue #6 comment #848: label inference
(delegated to gitea-labels-milestones), milestone assignment on create,
an assignee workaround for the blocked get_me/read:user scope, and the
"Depends on #N" dependency-linking convention validated by Gitea's
automatic cross-reference rendering.
Call signatures were re-verified live via ToolSearch against the deployed
gitea-mcp server rather than copied from api-reference.md, per ADR 0011 --
this caught that list_issues has no `type` or `milestones` parameter on the
live schema, despite the research doc documenting both (the exact drift
that caused issue #6 comment #849).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
Commit 7ad9fb6 (an orphaned parallel gitea-files authoring run, superseded
by 0c7dd04 during a worktree merge race) backfilled two real gotchas into
troubleshooting.md that the winning version didn't carry: protected-branch
signed-commit rejection and reverse-proxy 413 on large file writes, both
sourced from context7:/websites/gitea. Recovering them since they're
genuine findings, not duplicated elsewhere.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The gitea-branches skill was authored before the context7 research
backfill (workflow-conventions.md) landed on this branch, so its
sources.md was missing context7-websites-gitea and
context7-gitea-tea-cli — both present with status `extracted` in the
upstream research doc, which validate-provenance.sh requires every
consuming skill to account for. Adds context7-websites-gitea (credited
for the protected-branch gotcha) and context7-gitea-tea-cli (marked
`(none)` — its release/tag content is out of scope for branches/commits).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Covers get_file_contents, get_dir_contents, get_repository_tree,
create_or_update_file, delete_file — all verified working with the
current write:issue/write:repository token scope.
Cross-cutting skill for label and milestone operations, composed by
gitea-issues and gitea-prs. Includes the label inference guide deferred
from issue #6 comment #848.
Adds plugins/gitea/skills/gitea-branches/ per ADR 0011, covering
list_branches/create_branch/delete_branch (migrated from the flat
plugins/bin/skills/gitea/ dispatch) plus list_commits/get_commit (new
read-only commit-history domain). Call signatures were re-verified live
via ToolSearch against the deployed gitea-mcp server rather than copied
from api-reference.md, per issue #6 comment #849's root-cause fix.
Bumps the gitea plugin to 1.1.0 in both manifests for the new skill.
Existing gitea research docs were 100% code-derived from gitea-mcp
source with zero external content (the original docs.gitea.com fetch
timed out and was never retried). Adds workflow-conventions.md sourced
from context7 /websites/gitea and /git_gitea_com/gitea_tea: scoped/
exclusive label conventions, PR review/branch-protection rules,
release/tag semver conventions, and automatic issue/PR cross-reference
linking (validates the dependency-linking convention for issue #6).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
skill-author and agent-author SKILL.md files received bug fixes (git-log
commit-hash verification before reporting completion, skill-author now
forbids self-spawning audit/recheck subagents during its authoring pass,
and agent-author closed checklist/coverage gaps). Patch bump to reflect
fixed behavior, not new capability.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
The Prerequisites checklist mixed items to confirm (preconditions) with an
action to perform (capturing git log), so the following "stop and ask if
missing" gate didn't logically apply to the git-log step. The improve flow
also had no reminder to update source_keys/sources.md when an edit touches
research-sourced content, unlike the create flow's explicit step for it.
Refs #69
Independent skill-audit found that agent-author's closing checklists never
verified template <!-- --> comments were stripped from frontmatter (produces
invalid YAML if left in), the Copilot field-exclusion checklist omitted two
fields present in the authoritative list, and the improve flow had no
agent-audit availability check unlike the create flow.
Prior sessions had authoring subagents report completion after only
staging changes (git diff --stat showing output, but no git commit).
agent-author's create and improve flows now require capturing
git log --oneline -1 before and after the authoring pass and asserting
the hash actually changed via a real commit, matching the fix already
applied to skill-author.
Refs #69
Independent /skill-audit recheck flagged the git-log-capture instructions
as discoverable only at close-out (Step 6/Step 5), long after the step
where the hash should actually be snapshotted. Adds the capture checklist
item to Prerequisites (create flow) and Step 1 (improve flow) instead of
leaving it as a retrospective-only note. Also drops a sentence in the
improve flow's Step 4 that duplicated the preceding one on editing
scripts/reference files directly.
Refs #69
Prior sessions had authoring subagents report completion after only
staging changes (git diff --stat showing output, but no git commit),
and one run self-spawned its own audit/recheck subagent instead of
leaving that to forge's outer loop, losing an uncommitted draft when
the stray subagent's worktree was torn down.
Refs #69, #71
scripts/install.sh hardcoded $REPO_ROOT/.git/hooks, which breaks under any
git worktree checkout (.git is a file there, not a directory) — this is
what blocks every worktree-based agent from pushing cleanly. Resolve the
hooks directory via `git rev-parse --git-path hooks` instead, normalizing
to an absolute path since git returns it relative to the queried repo root
for plain checkouts but absolute for worktrees.
Also drops `agents`/`skills` fields from plugins/bin, plugins/core, and
plugins/gitea plugin.json where the referenced directories don't exist on
main yet (bin never had an agents/ dir; core and gitea's real skill/agent
content is still pending merge from an in-flight branch) — these were
failing scripts/check-manifests.sh and blocking pushes for unrelated work.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
skill-audit/agent-audit now proactively trigger after a skill/agent
file is hand-edited outside skill-author/agent-author, not just on
explicit request — closing a gap from this session where a fork's
direct edits to agent-author/agent-audit shipped without their own
inline audit until forge was invoked to check afterward.
Also: plugin-author gains a gotcha on claude plugin validate --strict
auto-discovering every .md under agents/ regardless of manifest
declarations (ADR-0010); agent-audit's dimension count and
validate-provenance.sh's --help now match actual behavior.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The gotcha claimed Gitea never auto-closes issues on merge. Confirmed
empirically (issue #63 / PR #64) that a regular merge preserving an
original commit's closing keyword does auto-close — only squash merges
(this skill's default) are unreliable. Also drops search_issues from
allowed-tools since no dispatch route calls it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Independent skill-audit clean-check surfaced that the dimension-mapping
list and manual-fallback checklist both skipped the counterpart-missing
case, which validate.sh already treats as a hard FAIL.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
`claude plugin validate --strict` auto-discovers every .md under a
plugin's agents/ directory as an agent requiring frontmatter, so the
provenance file there always needs fake agent frontmatter to pass
validation. Confirmed empirically that an explicit `agents` manifest
array can't suppress this discovery. Move the file to <plugin-root>/
sources.md instead, and update agent-author/agent-audit accordingly.
Adds ADR-0010, partially superseding ADR-0005's `agents/sources.md`
convention. Fixes#63.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
## Why
The git plugin only covered a partial slice of common git workflows.
This adds the remaining skill set (branches, commits, history, remotes,
submodules, workflow, worktrees) plus a git-orchestrate agent so the
plugin can handle end-to-end git automation instead of a handful of
commands.
## Implementation Notes
Each new skill was validated against its research docs and org
conventions after initial authoring, which surfaced hallucinated
version pins, factual errors, and completeness gaps that were
corrected in the same pass rather than left for follow-up.
## Impact
Bumps the git plugin to 1.3.0.
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Step 4 ensures that after creating/updating artifacts in a plugin, forge invokes plugin-author (clean-context subagent) to bump the plugin version if not already done by other skills. Prevents missed version updates when artifacts are added to plugins.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
kyberforge gains new forge skill for factory artifact routing; git gains pc-author and pc-run skills moved from kyberforge. Includes version parity fixes in CC manifests (ADR-0016).
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Grills intent, classifies target artifact type (skill/agent/plugin/marketplace
entry) against a fully descriptive table, then routes to the matching author
skill via fork subagent (falling back to inline when fork is unavailable or
the flow needs live interaction). Adds an independent clean-context audit
recheck after each skill/agent route, looping author-then-audit until the
recheck comes back clean, since the author skill's own inline audit shares
context with the work it verifies. Updates CONTEXT.md's Skill composition
entry to describe this recheck loop and adds forge's provenance chain
(references/sources.md).
Refs Defame1297/holocron#61
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Fills a gap needed for the planned forge orchestrator skill: neither doc set
previously stated when to build a skill vs a subagent/custom agent. Sourced
via context7 against the same libraries already recorded in each sources.md.
Also confirms agentskills.io's spec is runtime-agnostic and defines no agent
concept, so it has no bearing on this decision by design.
- agent-author: convert template comments from YAML (#) to HTML (<!-- -->)
- Easier to spot and distinguish from functional comments
- Add explicit "Delete template comments before shipping" reminders
- Update SKILL.md Steps 2-3 with removal instruction
- agent-audit: add comment-discipline check
- Flag excessive frontmatter documentation comments as padding
- Mirrors skill-audit's body-discipline principle
- Update coverage line to include comment-discipline dimension
This ensures agents follow the same comment-cleanup discipline as skills,
preventing template documentation from shipping with agent definitions.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
## Why
Two issues were found in `validate-provenance.sh` by `/skill-audit`:
1. `find_plugin_root` only walked up looking for bare `plugin.json`, missing
the `.claude-plugin/plugin.json` layout used by kyberforge plugins — matching
the logic already present in `validate.sh`.
2. Check numbers in `--help` and inline comments had a gap (0,1,2,4,5,6) from
a previously removed check, making the numbering confusing to readers.
## Implementation Notes
Check numbers renumbered sequentially 0–5 in both the `--help` output block
and the inline `# --- Check N:` comments. The `find_plugin_root` condition now
mirrors the `detect_scope` function in `validate.sh`.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0147vXtL5sP6vorDdqXGJJU9
Corrects three FAIL findings from the skill-audit run:
- Scope detection table in SKILL.md and references/scripts.md now lists all
four plugin-marker variants the script actually checks (plugin.json,
.claude-plugin/plugin.json, .plugin/plugin.json, .github/plugin/plugin.json)
- assets/README.md copilot.agent.md description was wrong about field set;
replaced with accurate CLI-format description noting excluded cloud/IDE fields
and the Copilot tool aliases actually used.
Also applies the SUGGESTION: moves the conditional reference
(`If the destination is a plugin directory, read references/deployment-modes.md`)
out of the ## Gotchas section body and into ## Route as a standalone line,
immediately after ## Gotchas closes.
INFO findings (source_keys frontmatter) were already present in both
references/README.md and references/scripts.md — no change needed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0147vXtL5sP6vorDdqXGJJU9
## Why
The description sentence "Handles both the full create flow (scaffold → fill →
validate) and the improve flow (signals → root cause → edit → audit)." describes
internal mechanics rather than user intent. The surrounding trigger phrases already
cover both create and improve intents, so this sentence adds no triggering value
and violates the description principle of focusing on what the user is trying to
achieve.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0147vXtL5sP6vorDdqXGJJU9
Remove phantom cross-file name-match claim from SKILL.md manual fallback
list (validate.sh has no such check). Fix broken bats stem-mismatch test
to overwrite the Copilot file instead of the CC file, exercising the
actual Copilot stem check.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0147vXtL5sP6vorDdqXGJJU9
- Fix validate.sh: remove incorrect name==stem check for CC files (CC docs say filename need not match name field); keep check for Copilot CLI only
- Fix validate.sh: plugin scope detection now checks both plugin.json and .claude-plugin/plugin.json
- Fix validate.sh: Copilot cloud/IDE agents (.github/copilot/agents/) have name as optional; path-based guard added
- Add validate.sh checks: Copilot body length >30,000 chars (SUGGESTION), Copilot-only fields in CC files (FAIL), subagent-unavailable tools in tools field (SUGGESTION)
- Add references/description-quality.md as conditional escape hatch for borderline description findings
- SKILL.md: name five audit dimensions in description; sharpen indirect-trigger phrasing
- SKILL.md: label pair-mandate as kyberforge project convention, not platform requirement
- SKILL.md: scope redundant name-match/body-empty checks to manual fallback only
- SKILL.md: add conditional reference to description-quality.md; update provider-safety description for new check categories; fix plugin scope gotcha to mention .claude-plugin/plugin.json
- SKILL.md: add INFO tier to result block template
- Add source_keys frontmatter to references/README.md; update sources.md to add description-quality.md to contributing files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0147vXtL5sP6vorDdqXGJJU9
