CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

issues

Track and recall all outstanding tasks, recommendations, and issues for this repo as durable cross-session memory. Use when the user types "/issues" (state the open items back), or asks to add/close/update/capture an outstanding task, recommendation, or issue. The memory lives in docs/outstanding-issues.md; a plain "/issues" is read-only.

Quality

84%

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

75%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.

A highly actionable, well-structured operational skill with copy-paste-ready commands and a clear read-back workflow. Its main weakness is conciseness: dated historical anecdotes and ledger-archaeology details are inlined where a leaner rule statement (or a separate history/deprecated reference) would serve better.

Suggestions

Move dated history — the ISSUES-LIST.html retirement (2026-08-18), the PR #1766/#1767 duplicate anecdote, and the #M6JNR8 pruning limitation — into a short 'History / deprecated' section or reference file, keeping only the currently applicable rule in the main flow.

Tighten the 'A row being open is not evidence that nobody is working on it' paragraph down to its actionable rule: before acting on a queued item, check open PRs for the touched route/component; drop the narrative example.

Sequence the validation into the mutation workflow as an explicit checkpoint (after queueing a request, run `npm run issues:check`-style verification and fix/retry), rather than leaving it as a standalone bullet in Writing rules.

DimensionReasoningScore

Conciseness

Mostly efficient operational guidance, but several passages carry dated historical rationale — the legacy ISSUES-LIST.html retirement ("retired on 2026-08-18"), the duplicate-PR anecdote ("PR #1766 and the duplicate PR #1767, four hours apart, 2026-08-09"), "until ledger #M6JNR8" — that could be tightened or moved to a deprecated/history section. Not 4 because these history blocks are more than minor trimming; not 2 because the core instructions themselves are dense and earn their tokens.

3 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `npm run issues:report -- --json`, the full issues:add/done/update/queue invocations with flags, and explicit-path git add/commit lines, plus concrete filters (`/issues P1`, `--agent-safe-wins`).

5 / 5

Workflow Clarity

The default read is a clear numbered 5-step sequence with an explicit no-mutation checkpoint, and a validation gate (`npm run check:outstanding-issues`) exists. Not 5 because that validation step is not sequenced into the mutation flows — it appears in Writing rules rather than as an explicit post-write checkpoint with a fix-and-retry loop.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections (Trigger, Default, Mutating subcommands, Capture discipline, Writing rules, canonical ledger, commit); no bundle files exist and none are needed for the core flow. Not 5 because the body exceeds a lean overview — the historical rationale sections (legacy register retirement, duplicate-PR policy) would fit better in a separate reference file.

4 / 5

Total

16

/

20

Passed

Description

88%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: concrete, third-person, with an explicit Use-when clause covering command and natural-language triggers. The only gap is a few missing synonyms (TODO, follow-up, backlog) that users might naturally say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Track and recall all outstanding tasks, recommendations, and issues", "add/close/update/capture" — and names where the memory lives (docs/outstanding-issues.md), comprehensively covering the skill's capabilities without padding.

5 / 5

Completeness

Explicitly answers both: what ("Track and recall all outstanding tasks, recommendations, and issues for this repo as durable cross-session memory") and when ("Use when the user types '/issues'... or asks to add/close/update/capture...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural triggers — "/issues", "add/close/update/capture an outstanding task, recommendation, or issue" — but common variations users might say such as "TODO", "follow-up", or "backlog" are absent. Not 5 because coverage lacks synonyms; not 3 because the included terms are ones users would actually say.

4 / 5

Distinctiveness Conflict Risk

A clear niche — this repo's outstanding-issues ledger keyed to the "/issues" command and docs/outstanding-issues.md — with minor overlap risk against generic task-management or todo-list skills. Not 5 because "track tasks" language is broad enough to occasionally collide with such skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 possibly missing (scripts/ledger-inbox.mjs, scripts/outstanding-issues.mjs)

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.claude/skills/issues/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.