Files
holocron/docs/issues/0027-cross-cutting-skills.md
Defame1297 c705a38809 docs: issue 0016 — skill implementation workflow grill
Produces docs/notes/skill-implementation-workflow.md with agreed conventions
for all Chunk 3 skill issues (0017–0028). Key decisions:

- Per-skill process: source discovery (sub-agent) → source review with
  licence/security check (sub-agent) → conflict check vs constitution +
  factory principles (sub-agent) → synthesis grill → co-write iteratively
- Bootstrap: write-eval (hand-written) → write-skill (hand-written) →
  write-docs (first factory-authored, phase 2 of 0018) → everything else
- Upstream review changed from per-chunk-start to per-skill
- `when:` and `references:` frontmatter fields added to authoring standard
- Sub-agent usage prescribed as named steps in the workflow
- HITL: human reviewed and approved conventions

Updates: PRD implementation decisions; issues 0016–0028 with specific
acceptance criteria; docs/spec/overview.md; ROADMAP Chunk 3 housekeeping note
(bootstrap order, cadence, acceptance criteria status); CONTEXT.md Source field
(per-skill cadence, references: companion field); LESSONS.md with three patterns
from the grill session.

Post-grill additions (same session): Step 6 (session handoff) added to the
workflow; handoff section appended to issue 0016; handoff checklist item added
to Chunk 3 closure issue (0028).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-17 17:06:35 +00:00

4.6 KiB

0027 — Cross-cutting skills: session-handoff, governance-check, git-commit-message, improve-codebase-architecture, triage, zoom-out, caveman

Type: HITL
Parent PRD: docs/prd/chunk-3-skills-library.md

What to build

The 7 cross-cutting skills (no single phase home). Three are new; four are preserved Pocock placeholders upgraded to the authoring standard. Authored via write-skill (0018), evals via write-eval (0017). caveman is kept as-is (no eval required — it is a formatting-only utility, not a content skill).

Skills, origins, and trigger descriptions:

Flat name Origin Trigger description
session-handoff New Session handoff, save context, pausing work
governance-check New Check this against governance rules, is this allowed
git-commit-message New Write commit message, conventional commit, git message
improve-codebase-architecture Preserved; frontmatter + standard added Improve architecture, refactor structure, codebase improvement
triage Preserved; fix dead references; frontmatter + standard added Triage this issue, categorise, prioritise
zoom-out Preserved; frontmatter + standard added Zoom out, big picture, what are we doing
caveman Kept as-is (token compression utility — no trigger change)

Key constraints per skill:

  • session-handoff: captures current state, next steps, decisions with rationale, and linked issue reference; prompts LESSONS.md extraction before closing; does NOT manage docs/spec/ — spec is updated in-PR, not at handoff
  • governance-check: validates proposed action against AGENTS.md (must reference AGENTS.md, not governance.md, now that AGENTS.md is the primary entry point post-0015)
  • git-commit-message: conventional commits format; derives from diff; does not invent scope or type
  • triage: remove dead references (AGENT-BRIEF.md, OUT-OF-SCOPE.md); add frontmatter and authoring standard sections
  • zoom-out: add frontmatter and authoring standard; merge into architect role revisited at Chunk 5 grill (this note should appear in the SKILL.md as a when-not: constraint or a note in failure handling)
  • caveman: no changes; no eval needed (not a content-generating skill)

Implementation notes

Follow the per-skill workflow defined in docs/notes/skill-implementation-workflow.md.

Known upstream sources to review:

  • mattpocock/skills — original improve-codebase-architecture, triage, zoom-out, caveman placeholders; record SHAs for adopted content
  • For new skills (session-handoff, governance-check, git-commit-message): search for prior art before writing from scratch

Acceptance criteria

  • All 7 SKILL.md files exist at .agents/skills/<skill-name>/SKILL.md; metadata.category: cross-cutting; authoring standard met (except caveman — kept as-is)
  • Dead references removed from triage and any other affected skills
  • governance-check references AGENTS.md as the governance source (not governance.md); requires AGENTS.md refactor (0015) to be complete
  • session-handoff explicitly excludes docs/spec/ management from its scope
  • zoom-out SKILL.md notes the Chunk 5 grill revisit for potential merge into architect role
  • source: fields populated for all Pocock-derived skills and any adopted upstream content
  • Each new or refactored skill has a co-located eval at .agents/evals/cross-cutting/<skill-name>/eval.yaml via write-eval; caveman exempt
  • install.sh deploys all 7 to ~/.agents/skills/
  • HITL: human runs behavioral test for each new/refactored skill
  • HITL: human reviews each SKILL.md and eval before committing
  • Per-skill process followed for all new/refactored skills: source discovery (sub-agent) → source review with licence/security check (sub-agent) → conflict check against constitution + factory principles (sub-agent) → synthesis grill → co-write iteratively
  • Trigger description for each skill tested against explicit, implicit, and negative queries before body written
  • when: frontmatter field present in all new/refactored SKILL.md files (caveman exempt)
  • source: and references: fields correctly populated or absent
  • eval.yaml for each new/refactored skill contains all 5 required test types (caveman exempt)
  • Body ≤500 lines for each skill
  • docs/spec/overview.md updated to reflect all skills deployed

Blocked by

  • 0015 (AGENTS.md must exist before governance-check can reference it correctly)
  • 0016 (per-skill workflow)
  • 0017 (write-eval)
  • 0018 (write-skill)