CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

propose-issue

Propose a GitHub issue as a MoltNet daemon task. Use when the user wants to turn a getlarge/themoltnet issue into an enriched fulfill_brief task proposal for daemon agents without claiming the issue locally, assigning it, creating a worktree, or using repo-internal task scripts.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

Highly actionable and well-sequenced content with strong validation checkpoints and a complete executable SDK example. The main weakness is token efficiency: the brief template and issue-fetching instructions are duplicated between the prose workflow and the embedded code snippet.

Suggestions

Deduplicate the brief structure: keep either the 'Recommended brief shape' markdown template in step 3 or the equivalent section inside the JS snippet, not both — reference one from the other to save ~40 lines.

Move the full SDK publishing snippet into a scripts/ file (e.g., scripts/propose-issue.mjs) invoked by the documented env-var command, keeping only a short excerpt inline in SKILL.md.

Consolidate issue-fetching guidance: step 2 describes fetching the issue and comments, and the JS snippet repeats that logic; state it once and let the snippet be the implementation.

DimensionReasoningScore

Conciseness

The body is directive and free of concept-explanation padding, but the brief structure is written out twice (the ~40-line 'Recommended brief shape' template in step 3 and again inside the JS snippet), and issue-fetch instructions appear in both step 2 and the snippet. More than minor trimming is available, so it fits 'mostly efficient but could be tightened' rather than anchor 4.

3 / 5

Actionability

Fully executable guidance: exact CLI commands with an npx fallback, a complete self-contained ESM SDK snippet, and the precise env-var invocation command. Copy-paste ready and covers the common end-to-end case with no gaps.

5 / 5

Workflow Clarity

A clear five-step sequence with explicit validation checkpoints at each risky step: stop on missing team/diary ids, stop on an empty token, ask if the issue is closed, preview and ask once before publishing, and stop rather than falling back to a human token, plus fallback paths for CLI/SDK availability.

5 / 5

Progressive Disclosure

A single-file skill with well-organized sections and clearly signaled external doc links, and the inline 110-line snippet is explicitly justified as intentionally self-contained for publishing outside the repo. At ~300 lines the snippet and brief template could still be split into scripts/references for a leaner SKILL.md, keeping it below anchor 5.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: it states a concrete capability, an explicit 'Use when' trigger clause with natural vocabulary, and clear scope boundaries that distinguish it from sibling skills. Only minor gains available from adding a few more natural trigger synonyms.

DimensionReasoningScore

Specificity

Names the concrete action ('Propose a GitHub issue as a MoltNet daemon task') with precise system vocabulary ('enriched fulfill_brief task proposal', 'daemon agents') and explicit exclusions ('without claiming the issue locally, assigning it, creating a worktree'). It lists a couple of concrete actions plus behavioral boundaries rather than a comprehensive multi-action list, so it sits above anchor 3 but below anchor 5.

4 / 5

Completeness

Explicitly answers both what ('Propose a GitHub issue as a MoltNet daemon task') and when ('Use when the user wants to turn a getlarge/themoltnet issue into an enriched fulfill_brief task proposal for daemon agents') with concrete trigger phrasing, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Natural terms a user of this system would say are present: 'Propose a GitHub issue', 'task proposal', 'daemon agents', 'turn a ... issue into'. A few natural phrasings are missing (e.g., 'publish a task', 'create a task from an issue'), which keeps it below comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche tied to a specific repo (getlarge/themoltnet) and system concepts (MoltNet daemon, fulfill_brief), and it explicitly differentiates from the sibling claiming behavior ('without claiming the issue locally, assigning it'), giving minimal conflict risk.

5 / 5

Total

18

/

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

getlarge/themoltnet

Path

.agents/skills/propose-issue/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.