task

AI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 skill body with executable commands and a real validation probe; the main weaknesses are repetitive actor-flag boilerplate and a long inline command block. No bundle files exist, so progressive disclosure is judged on section organization alone.

Suggestions

Reduce actor-flag repetition by defining the flag string once (e.g., `ACTOR="--agent ... --agent-type ... --pid ... --session ..."`) and referencing it, or by showing the full form once and abbreviated forms after.

Consider moving the full canonical-command catalog into a references file, keeping only the create/phase/evidence/close essentials inline in SKILL.md.

Tighten the "Identify self" section — steps 5 and 6 overlap with the canonical-commands intro and could be merged.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no generic explanations of what a task is), but the four actor flags are repeated verbatim across ~12 commands and the "Identify self" guidance is restated in the canonical-commands intro, offering minor trim opportunities.	4 / 5
Actionability	Provides fully executable, copy-paste-ready `npx ai-devkit@latest task ... --json` commands covering the common cases (create, assign, status, phase, progress, next, blocker, evidence, artifact, show, list, close).	5 / 5
Workflow Clarity	Clear sequencing with an explicit validation checkpoint (read probe must exit 0; otherwise continue without logging) and a feedback loop (blocker add → resolve → status active), but it is a logging helper rather than a fragile operation, so the anchor-5 bar of full error-recovery loops/checklists is only partially met.	4 / 5
Progressive Disclosure	A single self-contained file with well-organized, clearly headed sections (Core idea, Identify self, Canonical commands, When to emit, Tips) and no broken or nested references; the long inline canonical-commands block is the only borderline bulk that might suit a reference file.	4 / 5
	Total	17 / 20 Passed

Description

80%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, specific description that names concrete recorded fields and a clear niche, with only minor gaps in trigger phrasing and synonym coverage. Promoting it to a 5 would require an explicit "Use when..." trigger clause with broader natural synonyms.

Suggestions

Add an explicit trigger clause such as "Use when working on a durable dev-lifecycle or structured-debug task and the user wants progress, phase, blocker, or validation tracking."

Broaden trigger terms with synonyms users might actually say (e.g., "task tracking", "log progress", "debug log", "status report").

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete recorded actions — "phase, progress, next step, blockers, and validation evidence" — giving comprehensive coverage of the task-tracking capability.	5 / 5
Completeness	Clearly states what (track progress via the ai-devkit task CLI) and implies when (dev-lifecycle / structured-debug work on a durable task), but the "Use to record..." clause states purpose rather than an explicit "Use when..." trigger, so the when could be more specific.	4 / 5
Trigger Term Quality	Includes natural developer-facing terms ("dev-lifecycle", "structured-debug", "progress on a durable task", "blockers", "validation evidence") but lacks common synonyms or extension-style variants, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct — durable task progress tracking via the ai-devkit task CLI scoped to dev-lifecycle and structured-debug — with only minor overlap risk against generic task-management skills.	4 / 5
	Total	17 / 20 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: codeaholicguy/ai-devkit
Path: skills/task/SKILL.md
Commit: d56e554

Reviewed: 3 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.