Fable audit
A kit for building with AI agents and also the engineering patterns around it.
npx -y skills add deepklarity/harness-kit --skill fable-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Audit 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 roadmap going', 'audit progress', or /fable-audit.
SKILL.md
2.3 KB, as published. Nobody here has run it
Fable roadmap auditor
Trust nothing; verify everything. Lean by user directive: an audit is one short report plus two file updates — not a documentation pass.
- Verify claims with proof. For each task DONE since the last audit, run its
verify step or inspect the merged artifact. Delegate command runs and file
checks to parallel haiku subagents; keep judgment in the main conversation.
The board is truth (
board_overview.py/spec_trace.py/task_inspect.py --brieffromtaskit/taskit-backend/); doc-vs-board divergence is a finding. Downgrade anything unprovable. - Recompute what has data: run the suites; count autonomy/unsticks from board history (hand-counted until the metrics script lands — say so). Report gaps as gaps.
- Grade against
SCORECARD.md— every score move names the anchor (0/5/10) its evidence supports; recompute the overall (plain average). Scores live only in thefable_roadmap.mdtable — a score anywhere else is a finding. Then judge the ladder againstfable_roadmap.mdexit criteria; check the ratchet rules there. Violations are findings. - Write
audits/YYYY-MM-DD*.md: verdict line (on track / drifting / blocked + why), verified-done table with proof, demotions, metrics snapshot, top-3 risks with mitigations, ladder call. Readable in 30 seconds from the top. - Update the living docs: RESUME "Current state" + BACKLOG re-rank (the top IS the next wave draft) + the ladder Status column if a level changed.
- Artifact only if the user asks — redeploy to the URL in RESUME's durable facts; never mint a new one.
--dispatchonly: convert the backlog top into a wave spec underbootstrap/and load it (pre-dispatch checklist in the loader templates).
End with: verdict line, ladder level, top 3 next actions — plain prose.