CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

harvest

Report where a session missed moo's standard — the agent asks only while stating intent and shape, then works on its own — as issues a builder can act on. Pass a session id to report on a past session instead of this one.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./hunch/skills/harvest/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary procedural skill: lean, fully executable, with a clearly sequenced workflow and robust validation/feedback loops (scrub-retry, yes-gate, re-review of changed drafts). Its one real defect is bundle integrity — three of the six referenced paths (kinds/, issue.md, comment.md) do not exist in the shipped bundle, leaving the detection and drafting steps without their promised inputs.

Suggestions

Ship the missing `kinds/` files referenced by the Detect section ("Read every file in `${CLAUDE_SKILL_DIR}/kinds/`"), or inline the kind definitions if the directory is not part of the bundle.

Add the missing `issue.md` and `comment.md` templates referenced by the Draft section, or replace the references with the layout content inline.

Consider referencing `scripts/scrub.test.sh` (present but unreferenced) from the body so the bundle's test coverage is discoverable.

DimensionReasoningScore

Conciseness

The ~63-line body is pure procedure with zero padding and no explanations of concepts Claude already knows — every line instructs ("Run `${CLAUDE_SKILL_DIR}/scripts/read.sh <id>`... It fails → show its error and stop"). Matches 'lean and efficient; assumes Claude's competence; every token earns its place'; not 4 because the over-explanation-that-could-be-trimmed in that anchor is entirely absent.

5 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: `read.sh <id> <turn>`, `past.sh`, `gh issue view <N> -R saadshahd/moo.md --comments`, `mktemp`, `scrub.sh <id> <draft>`, and the complete issue pipeline `tail -n +2 <draft> | gh issue create -R saadshahd/moo.md --label harvest --title "$(sed -n '1s/^Title: //p' <draft>)" --body-file -`, plus a concrete five-row decision table. Matches 'fully executable; copy-paste ready'; not 4 because there are no gaps in the commands — every placeholder (<id>, <turn>, <draft>, <N>) is defined.

5 / 5

Workflow Clarity

A clear nine-phase sequence (Read → Detect → Name the opportunity → Value → Match past issues → Draft → Scrub → Show → File on yes) with explicit validation and feedback loops: "It fails → show its error and stop", "Exit 1 → replace each term it lists with a placeholder and run it again", "Never show a draft that has not passed", the reporter's yes-gate, and "A draft changed after the yes goes back through Scrub and Show". The outward-facing filing operations carry full validation, so the missing-validation cap does not apply; matches the explicit-validation-with-feedback-loops anchor.

5 / 5

Progressive Disclosure

Section structure is clean and references are one level deep, but scored against the actual bundle: of the six referenced paths, `scripts/read.sh`, `scripts/past.sh` and `scripts/scrub.sh` exist while `${CLAUDE_SKILL_DIR}/kinds/`, `${CLAUDE_SKILL_DIR}/issue.md` and `${CLAUDE_SKILL_DIR}/comment.md` are absent from the bundle. The Detect step ("Read every file in `${CLAUDE_SKILL_DIR}/kinds/`") and the Draft templates depend entirely on files that are not shipped, so navigation fails exactly where detail is deferred. Missing half the referenced paths is beyond anchor 4's 'minor organization gaps'; anchor 3 fits the impact.

3 / 5

Total

18

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear, distinctive 'what' with the standard defined inline, but omits any 'when to use it' trigger guidance and leans on insider jargon ("moo's standard", "intent and shape") that a user outside the moo ecosystem would not naturally say. It sits at the midpoint of the rubric: precise about purpose, weak on invocation cues.

Suggestions

Add an explicit 'Use when...' clause or equivalent trigger guidance, e.g. 'Use when the user asks to harvest, audit, or report problems from a moo session' — this would lift completeness and trigger_term_quality together.

Include natural synonyms a user might say ("audit this session", "find what the session got wrong", "harvest session <id>") alongside the existing 'session' and 'report' keywords.

Briefly gloss the insider terms: replace or annotate 'moo's standard' and 'intent and shape' with wording a user outside the moo ecosystem would recognize.

DimensionReasoningScore

Specificity

"Report where a session missed moo's standard ... as issues a builder can act on" names the domain and output, and even defines the standard inline ("the agent asks only while stating intent and shape, then works on its own"), but covers only 1-2 concrete actions rather than the full capability set (matching past issues, scrubbing, drafting comments). This matches the anchor for naming domain and 1-2 concrete actions, not the level above (several specific actions listed) nor below (actions are more than minimal or generic).

3 / 5

Completeness

The 'what' is clearly stated (report standard-misses as builder-actionable issues), but there is no 'Use when...' clause or equivalent explicit trigger guidance; "Pass a session id to report on a past session instead of this one" is an argument-usage note, not a when-to-use trigger. Per the judging guidelines a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Some natural keywords are present ("session", "session id", "report", "issues") but common variations and synonyms are missing, and insider jargon ("moo's standard", "intent and shape") dominates. Matches 'some relevant keywords but missing common variations'; not 4 because a natural 'Use when...' trigger phrase set is absent, not 2 because the terms are domain-relevant rather than purely generic.

3 / 5

Distinctiveness Conflict Risk

"Report where a session missed moo's standard" carves a clear niche (session auditing against a named standard, filing harvest issues) with minimal overlap risk against other skills. Not 5 because the anchor expects distinct explicit triggers, which the description lacks; not 3 because the scope is far more specific than the generic-overlap examples.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saadshahd/moo.md

Path

hunch/skills/harvest/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.