plan

Use ONLY when the user explicitly asks to plan a task, create a task file, produce a task breakdown in the accepted format, or prepare a critiqued strategy before coding. Writes under the `tasks` role. Not for design chat or ad-hoc code suggestions.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/flowai/skills/plan/SKILL.md

Quality

Content

62%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 thorough, highly actionable planning procedure with strong workflow sequencing and validation, but it is hampered by heavy verbosity and a monolithic structure that inlines reference-grade detail instead of progressively disclosing it. Tightening prose and splitting detailed references into separate files would lift the two lowest dimensions.

Suggestions

Trim meta-commentary, dated incident asides, and justifications for why rules exist — state each rule once and trust the reader (targets conciseness).

Move detailed reference material (SALP row formats, variant archetype definitions, surface-scout dispatch protocol) into files under references/ and link to them one level deep, leaving SKILL.md as an overview (targets progressive_disclosure).

Renumber the step-5 sub-steps into execution order (5a, 5b, 5c) so the sequence reads top-to-bottom without jumping (targets workflow_clarity).

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: extensive meta-commentary justifying why each rule exists, repeated emphatic markers ('CRITICAL', 'MUST', 'FORBIDDEN'), and dated incident asides ('observed 2026-09-06', 'plan-affected-surface-scout') pad the text well beyond what the procedure requires, adding several unnecessary explanatory sections rather than trusting the reader.	2 / 5
Actionability	Provides concrete, executable guidance — exact YAML frontmatter shape with a canonical example, SALP row format strings, specific commands (`date +%Y-%m-%d`, `mkdir -p`), and precise bullet formats — with only minor gaps where it defers to external AGENTS.md for the accepted task format and SRS layout.	4 / 5
Workflow Clarity	A clearly sequenced eight-step workflow with explicit validation checkpoints (Acceptance Tuple Check, completeness check, surgical-edit constraints), feedback loops (surface-scout dispatch/collect/degradation, critique→triage→apply), and a closing verification checklist — matching the top anchor for explicit validation and error-recovery loops; the out-of-order 5a/5c/5b sub-step numbering is a minor blemish but does not break the sequence.	5 / 5
Progressive Disclosure	No bundle files exist and the entire ~160-line body is a single monolithic SKILL.md; section headers provide some structure, but large blocks of reference-grade detail (SALP formats, variant archetype rules, surface-scout dispatch protocol) are inlined rather than split into one-level-deep reference files, and the under-50-line simple-skill exception does not apply.	3 / 5
	Total	14 / 20 Passed

Description

87%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, third-person description that concretely states what the skill does, when to use it via natural user phrasing, and where it is out of scope. The only soft spot is specificity, where the actions are slightly abstract relative to the most concrete anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('plan a task, create a task file, produce a task breakdown in the accepted format, or prepare a critiqued strategy before coding') plus the concrete artifact constraint 'Writes under the `tasks` role', but the actions sit at a slightly abstract planning level rather than fully comprehensive concrete operations, so it sits just below the top anchor.	4 / 5
Completeness	Explicitly answers both 'what' (create a task file / produce a task breakdown / prepare a critiqued strategy, writes under the `tasks` role) and 'when' ('Use ONLY when the user explicitly asks to...') with concrete trigger phrases and a negative boundary ('Not for design chat or ad-hoc code suggestions'), matching the top anchor.	5 / 5
Trigger Term Quality	Natural user phrasing is well covered ('plan a task', 'create a task file', 'task breakdown', 'critiqued strategy before coding') and directly mapped to a 'Use ONLY when the user explicitly asks to...' trigger, though a few common synonyms/variations are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (planning under the `tasks` role) with an explicit 'Use ONLY when' trigger and an explicit negative scope ('Not for design chat or ad-hoc code suggestions'), giving it distinct triggers and minimal conflict risk with adjacent skills.	5 / 5
	Total	18 / 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: ad81ae6

Reviewed: 4 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.