plan

Use ONLY when the user explicitly asks to plan a task, create a role-resolved task file, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Writes tasks under the `tasks` role with extended frontmatter. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured, highly actionable planning skill body with a clear sequenced workflow and embedded validation checkpoints. The main weakness is mild verbosity from repeated emphatic phrasing and dependence on external AGENTS.md references rather than bundled progressive-disclosure files.

Suggestions

Collapse the recurring 'execute immediately, no permission needed' and 'CRITICAL' emphasis into a single stated convention once, then rely on it, to tighten conciseness.

Consider bundling the GODS format template and AGENTS.md Planning Rules into a references/ file linked from the body, so the detailed material lives one level deep instead of being assumed from an external project file.

Trim the duplicated allow-list/SRS-surgical-edit rationale between the Rules section and the step 5c instructions to a single authoritative statement.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence (no padding about what planning or frontmatter is), but repeated emphatic markers like 'CRITICAL', 'MUST', and the recurring 'execute immediately, no permission needed' phrases could be trimmed without losing clarity.	4 / 5
Actionability	Concrete executable guidance throughout — exact frontmatter keys and order, a copy-paste YAML example, specific SALP row formats, idempotency rules, and mkdir/verification commands — fully actionable for the common cases.	5 / 5
Workflow Clarity	Steps 1–8 are clearly sequenced with explicit validation checkpoints (5a Acceptance Tuple Check, 5c idempotency checks, the final Verification checklist) and feedback loops (re-validate after fixes); the operation is not destructive/batch so no cap applies.	5 / 5
Progressive Disclosure	The single SKILL.md is well-organized into Overview, Context, Rules, Question Format, Instructions, Output Format, and Verification sections, but it relies heavily on inline references to external AGENTS.md sections rather than bundled reference files, leaving minor navigation gaps for the detailed GODS format and Planning Rules.	4 / 5
	Total	18 / 20 Passed

Description

92%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, highly specific description with explicit 'Use ONLY when' trigger guidance and negative triggers that bound the skill's applicability. Minor room to add natural user synonyms for planning, but it clearly communicates both capability and invocation conditions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'plan a task', 'create a role-resolved task file', 'produce a GODS-format breakdown', 'prepare a critiqued implementation strategy', 'Writes tasks under the `tasks` role with extended frontmatter' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers both 'what' (writes GODS-format tasks under the `tasks` role with extended frontmatter) and 'when' via the 'Use ONLY when the user explicitly asks to plan a task...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	The natural phrase 'plan a task' and the explicit negative triggers ('how would you approach X?') are present, but common synonyms a user might actually say (e.g. 'break down this work', 'scope this out', 'write a plan') are missing, so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	The GODS-framework niche and the explicit 'Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions' negative triggers sharply distinguish it from general coding/design skills with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/plan/SKILL.md
Commit: b4ba256

Reviewed: ~22 hours 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.