project-planner

Detects stale project plans and suggests session commands. Triggers on: sync plan, update plan, check status, plan is stale, track progress, project planning.

1.54x

Quality

—

Does it follow best practices?

Impact

94%

1.54x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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

A clean, well-structured instruction-only skill with concrete slash-command guidance and clear detection scenarios. The main improvement is reducing repetition between the Detection Logic, Quick Reference, and Notes sections.

Suggestions

Collapse the 'Quick Reference' table into the Detection Logic section or remove it, since it duplicates the per-scenario suggestions already shown above.

Merge the 'Notes' section into 'Purpose' to avoid restating 'only suggests, never modifies' and the single-source-of-truth point twice.

Optionally convert the illustrative detection blocks (e.g. 'docs/PLAN.md last modified: 5 days ago') into a compact checklist so the actionable signal is even denser.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the 'Quick Reference' table largely restates the Detection Logic scenarios and the 'Notes' section repeats the Purpose/never-modifies point, so it could be tightened; this matches the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Guidance is concrete and copy-paste ready with specific slash commands ('/sync --git', '/save "notes"', '/save --archive') and precise staleness heuristics (>3 days, commits since, feat:/fix:/refactor:); as an instruction-only skill this satisfies the actionable bar without executable code.	3 / 3
Workflow Clarity	The detect-then-suggest flow is laid out unambiguously across four enumerated scenarios (Plan Missing, Plan Stale, Uncommitted Work, Session Start), and as a suggest-only skill with no destructive or batch operations the missing-validation cap does not apply.	3 / 3
Progressive Disclosure	A single well-organized file with clearly headed sections (Purpose, Detection Logic, Quick Reference, Staleness Heuristics, Notes) and no nested external references; with no bundle files present, the well-organized single-file structure meets the level-3 bar for simple skills.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 concise, third-person description that clearly states both capability and explicit trigger terms with good natural-language coverage. Its only weakness is that the capability list is brief rather than enumerating multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('stale project plans') and two actions ('Detects' and 'suggests session commands'), but does not enumerate a comprehensive list of specific concrete actions, matching the 'names domain and some actions' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill does ('Detects stale project plans and suggests session commands') and gives explicit when-guidance via the 'Triggers on:' clause, satisfying both halves; the trigger clause avoids the level-2 cap for missing trigger guidance.	3 / 3
Trigger Term Quality	'Triggers on: sync plan, update plan, check status, plan is stale, track progress, project planning' gives good coverage of natural phrases a user would say, matching the level-3 anchor for natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	The project-plan/staleness niche with distinct sync/save triggers is clearly scoped and unlikely to fire for unrelated skills, matching the level-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.