init

Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.

Quality

63%

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

Fix and improve this skill with Tessl

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

Quality

Content

73%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.

The body is a well-structured, highly actionable multi-step workflow with strong validation checkpoints and feedback loops for its destructive operations. Its main weakness is mild redundancy across rules and steps that could be consolidated for token efficiency.

Suggestions

Consolidate the repeated per-file diff/confirmation guidance into a single authoritative statement to remove redundancy between rules 3/8 and the step bodies.

State the legacy-cleanup requirement once (e.g. in step 4) and have later steps and the checklist reference it rather than re-explaining.

Either inline the analyzer's exact JSON field contract once or point to it in a reference, instead of re-asserting field names across multiple steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with little concept-explanation padding, but contains noticeable redundancy (diff/confirmation guidance repeated in rules 3 and 8 and across steps; legacy cleanup repeated in steps 4, 7, and the checklist) that could be tightened, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Provides concrete executable commands (deno run --allow-read scripts/generate_agents.ts .), exact JSON shape, specific file paths, full interview prompt, and explicit git rm/symlink targets; minor gaps remain where delegation is high-level ('Read and follow its SKILL.md') and the analyzer JSON contract is asserted rather than shown verbatim.	4 / 5
Workflow Clarity	Twelve clearly numbered steps with explicit Greenfield/Brownfield conditions, per-file diff confirmations, a dedicated verification checklist, and a validate-then-fix-retry loop (step 12 re-run, check verification.passed, fix before proceeding) — explicit validation and feedback loops for destructive/batch operations.	5 / 5
Progressive Disclosure	References a single one-level-deep template (assets/AGENTS.template.md, confirmed present) and the analysis script with clear purpose signaling; structure is good with most procedural content appropriately inlined, though the bulk of detail lives inline rather than split into further reference files.	4 / 5
	Total	16 / 20 Passed

Description

53%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.

The description conveys a clear purpose and niche but lacks any 'Use when' trigger guidance and uses skill-specific jargon rather than natural user phrases. It meets a competent-but-not-exemplary bar across the dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when bootstrapping agent documentation for a new or existing project.'

Surface 1-2 natural trigger phrases a user would actually say (e.g. 'setting up AGENTS.md', 'onboarding an agent to a codebase').

List a concrete action or two (e.g. '...generates a root AGENTS.md with a CLAUDE.md symlink') to lift specificity above the minimal-action anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (AGENTS.md and rules) and two concrete sub-cases (Greenfield/Brownfield), but the actions themselves are minimal ('Initialize... handling'); not a list of several specific actions, so it sits at the anchor-3 level rather than 4.	3 / 5
Completeness	It states a clear 'what' (initialize project with AGENTS.md and rules) but has no 'when'/'Use when' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('Initialize project', 'AGENTS.md', 'Greenfield', 'Brownfield') but they are skill-specific jargon with no natural synonyms or common variations a user would naturally say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Greenfield/Brownfield framing carves a clear niche for agent-doc bootstrapping with only minor overlap risk against generic project-setup skills, fitting the 'mostly distinct' anchor.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/init/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.