Compare

Asset-only retrospective. No transcript re-scan, no LLM re-analysis, no HITL. Triggers: "compare", "review past", "what changed", "self retrospective".From its SKILL.md

Install

npx -y skills add jazz1x/honne --skill compare

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 3 commands, including `bash "${CLAUDE_PLUGIN_ROOT}/scripts/query-assets.sh" --tag "<axis>" --scope "$SCOPE" --type claim --out stdout` and 2 more.

SKILL.md

2.3 KB, 322 tokens by cl100k_base, as published. Nobody here has run it

compare — Read-only Retrospective

Step 1: Scope HITL (one-shot)

Ask: "Retrospective scope — repo or global?"

Step 2: Assets presence check

If .honne/assets/ absent or empty: Print "No assets yet. Run honne first." and exit 0.

Step 3: Load claims + evolutions

bash "${CLAUDE_PLUGIN_ROOT}/scripts/query-assets.sh" \
  --tag "<axis>" --scope "$SCOPE" --type claim --out stdout

bash "${CLAUDE_PLUGIN_ROOT}/scripts/query-assets.sh" \
  --type evolution --scope "$SCOPE" --out stdout

Async wait pattern — use Monitor until-loop, not sleep N && cat:

# ✓ Monitor: until [ -f ".honne/assets/claim.jsonl" ]

Step 4: Time-bucket grouping

Group by axis × recorded_at bucket (YYYY-MM granularity for MVP).

Step 5: Render docs/honne-compare.md (+ stdout)

Format per architecture PRD §4.2 compare Step 6. No LLM unless the user asked for "summarize" — and even then, only cite-bound.

Step 6: Asset immutability check

This skill MUST NOT write to .honne/assets/ or .honne/persona.json. Verify (test): stat -c %Y on assets/*.jsonl before/after unchanged.

What ships with it: 2 files

5.1 KB alongside SKILL.md

SKILL.jp.md2.7 KB
SKILL.ko.md2.4 KB