fable-audit
starsforks
How to install fable-audit?
deepklarity/harness-kit/fable-audit
$npx -y skills add deepklarity/harness-kit --skill fable-auditAudit the fable roadmap (docs/fable_roadmap/) — verify claimed progress with proof, write a short report, update RESUME state + BACKLOG rank. Use at wave close or whenever the user asks how roadmap development is going. Triggers on - 'fable audit', 'roadmap audit', 'how is the ro
SKILL.md
| 1 | # Fable roadmap auditor |
| 2 | |
| 3 | Trust nothing; verify everything. Lean by user directive: an audit is one short |
| 4 | report plus two file updates — not a documentation pass. |
| 5 | |
| 6 | 1. **Verify claims with proof.** For each task DONE since the last audit, run its |
| 7 | verify step or inspect the merged artifact. Delegate command runs and file |
| 8 | checks to parallel haiku subagents; keep judgment in the main conversation. |
| 9 | The board is truth (`board_overview.py` / `spec_trace.py` / |
| 10 | `task_inspect.py --brief` from `taskit/taskit-backend/`); doc-vs-board |
| 11 | divergence is a finding. Downgrade anything unprovable. |
| 12 | 2. **Recompute what has data**: run the suites; count autonomy/unsticks from |
| 13 | board history (hand-counted until the metrics script lands — say so). |
| 14 | Report gaps as gaps. |
| 15 | 3. **Grade against `SCORECARD.md`** — every score move names the anchor |
| 16 | (0/5/10) its evidence supports; recompute the overall (plain average). |
| 17 | Scores live only in the `fable_roadmap.md` table — a score anywhere |
| 18 | else is a finding. Then judge the ladder against `fable_roadmap.md` |
| 19 | exit criteria; check the ratchet rules there. Violations are findings. |
| 20 | 4. **Write `audits/YYYY-MM-DD*.md`**: verdict line (on track / drifting / |
| 21 | blocked + why), verified-done table with proof, demotions, metrics snapshot, |
| 22 | top-3 risks with mitigations, ladder call. Readable in 30 seconds from the top. |
| 23 | 5. **Update the living docs**: RESUME "Current state" + BACKLOG re-rank (the top |
| 24 | IS the next wave draft) + the ladder Status column if a level changed. |
| 25 | 6. **Artifact only if the user asks** — redeploy to the URL in RESUME's durable |
| 26 | facts; never mint a new one. |
| 27 | 7. **`--dispatch` only**: convert the backlog top into a wave spec under |
| 28 | `bootstrap/` and load it (pre-dispatch checklist in the loader templates). |
| 29 | |
| 30 | End with: verdict line, ladder level, top 3 next actions — plain prose. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
