adapt

Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of update.

Quality

67%

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/adapt/SKILL.md

Quality

Content

81%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 highly actionable, well-sequenced orchestration skill with strong validation feedback loops and a real template asset reference. Its only real weakness is verbosity in the subagent-waiting and template-location passages that could be trimmed.

Suggestions

Compress the 'Waiting means collecting, not listening' and 'Present nothing while an adapter is outstanding' passages into a single terse rule with one short rationale, removing the restated examples.

Move the multi-tier install-mode AGENTS.template.md location list into a short decision rule or a reference snippet, keeping only the precedence order inline.

Trim restated guidance that recurs across steps 3, 4, and 7 (the collection/waiting rule) by defining it once and back-referencing it.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and operational, but the extended 'Waiting means collecting, not listening' passage, the repeated 'Present nothing while an adapter is outstanding' elaboration, and the long install-mode template-location enumeration could be tightened without losing clarity.	3 / 5
Actionability	Concrete, copy-paste-ready commands appear throughout (git show HEAD:<path>, git diff HEAD --, git checkout HEAD --, git diff --no-index), alongside named subagents (skill-adapter, agent-adapter) and exact IDE dir paths covering the common cases.	5 / 5
Workflow Clarity	A clear 7-step sequence is given with explicit validation checkpoints (diff-replacement check, byte-for-byte frontmatter verification, stale-command re-verification), revert feedback loops, and a closing verification checklist for the batch/overwriting operation.	5 / 5
Progressive Disclosure	Content is organized into well-signaled tagged sections (<context>, <rules>, <step_by_step>, <verification>) with a one-level-deep reference to the verified assets/AGENTS.template.md bundle; the inline install-mode enumeration is the main organization gap keeping it from a 5.	4 / 5
	Total	17 / 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 clearly states what the skill does and names its targets, but omits an explicit 'Use when...' trigger and leans on domain jargon over natural user phrases. It is distinct from sibling skills yet mid-tier on completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g., 'Use after first project-local flowai install, after a stack change, or when generic deno/npm examples need replacing with project-specific commands.'

Surface natural user phrases and synonyms ('adapt skills to my project', 'switch stack commands', 'localize flowai') so the description matches what users actually say.

Expand the action beyond a single verb to concrete operations ('swap generic commands, re-point examples, verify artifacts against templates') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates four concrete resource types (skills, agents, AGENTS.md artifacts, hooks), but the single action verb 'Adapt...to project specifics' leaves the action set non-comprehensive rather than listing multiple distinct operations.	3 / 5
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'Standalone adaptation — independent of update' only weakly implies when, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Domain keywords like 'adapt', 'skills', 'agents', 'hooks', and 'AGENTS.md' are present, but it lacks the natural trigger phrases a user would actually say (e.g., 'after installing flowai', 'switch my stack', 'update project commands') and their common variations.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (adapting project-local flowai primitives) and explicitly distinguishes itself from the 'update' skill, leaving only minor overlap risk with that closely related command.	4 / 5
	Total	13 / 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: 1 missing	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/adapt/SKILL.md
Commit: ad81ae6

Reviewed: 8 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.