CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-task-backlog-hygiene

Audit Codex tasks and preserve unowned outcomes in `BACKLOG.md` while closing completed or superseded chats. Use when Codex task ownership or archive state needs cleanup, not generic issue-tracker or project-backlog work.

67

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tightly written, highly actionable instruction skill with a clear workflow and explicit validation for destructive archive operations. Minor room to add a worked example or move detailed classification guidance into a reference file.

DimensionReasoningScore

Conciseness

Lean, directive prose with no padding and no explanation of concepts Claude already knows; every line earns its place, matching the top anchor.

5 / 5

Actionability

Provides a concrete classification taxonomy, a literal BACKLOG.md template, and specific decision rules; as an instruction-only skill code absence is not penalized, but it lacks a worked end-to-end example, keeping it just below 5.

4 / 5

Workflow Clarity

Clear sequence (scope → classify → preserve → uncertainty → close) with an explicit reporting checklist and a validation guard ('Never claim a task was archived... unless the operation succeeded') for destructive batch archive ops.

5 / 5

Progressive Disclosure

Well-organized single file with clear sections and no nested references; stays just below 5 because the body (~105 lines) slightly exceeds the simple-skill carve-out and has no external split.

4 / 5

Total

18

/

20

Passed

Description

71%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, concrete description that answers both what and when and explicitly disambiguates itself from adjacent skills. The main gap is slightly narrower trigger-term coverage rather than any vagueness.

DimensionReasoningScore

Specificity

Names several concrete actions ('Audit Codex tasks', 'preserve unowned outcomes in BACKLOG.md', 'closing completed or superseded chats'), matching the 'several specific actions, minor gaps' anchor; not a 5 because the action set is not comprehensively enumerated.

4 / 5

Completeness

Explicitly answers both what (audit/preserve/close) and when ('Use when Codex task ownership or archive state needs cleanup'), plus a negative boundary; not a 5 because the trigger phrasing is single rather than multi-phrased like the canonical 5 example.

4 / 5

Trigger Term Quality

Uses natural terms a user would say ('Codex tasks', 'archive state', 'cleanup') with good coverage; stays just below 5 because common synonyms and phrasings are limited and the vocabulary is niche.

4 / 5

Distinctiveness Conflict Risk

The 'not generic issue-tracker or project-backlog work' clause carves out a clear niche with distinct Codex-desktop triggers and minimal conflict risk, matching the top anchor.

5 / 5

Total

17

/

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
EpicenterHQ/epicenter
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.