conductor-revert

Git-aware undo by logical work unit (track, phase, or task)

1.60x

Quality

65%

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/conductor-revert/SKILL.md

The canonical home for this skill is conductor-revert in sickn33/agentic-awesome-skills

Quality

Content

77%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 strong, executable workflow with excellent validation and safety handling for a destructive git operation. Its main weaknesses are verbosity from repeated ASCII template blocks and a broken reference to a non-existent playbook file.

Suggestions

Fix or remove the reference to resources/implementation-playbook.md (the file does not exist), or create it so the progressive-disclosure pointer resolves.

Condense the repeated ASCII banner frames into a shared template convention to reduce token cost while preserving the exact UX output.

Consider moving the large edge-case and conflict-resolution templates into a reference file with a clear one-level-deep pointer to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Accurate and specific with no concept over-explanation, but the repeated large ASCII banner/template blocks (execution plan, warning, conflict, verification) consume tokens and could be tightened, fitting 'Mostly efficient but could be tightened.'	3 / 5
Actionability	Provides fully executable git commands (git log --grep, git revert --no-edit) with realistic example SHAs and messages, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases.'	5 / 5
Workflow Clarity	Clear multi-step sequence (pre-flight, target selection, discovery, plan, execution, updates, verification) with explicit validation checkpoints, halt-on-conflict feedback loops, and a safety-rules checklist; the destructive-op cap does not apply because validation is thorough.	5 / 5
Progressive Disclosure	Well-sectioned with headers but essentially monolithic; it references 'resources/implementation-playbook.md' which does not exist and no bundle files are provided, fitting 'Some structure... references present but not clearly signaled; content that should be separate is inline.'	3 / 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 is concise and names a distinct niche with concrete work units, but it lacks an explicit 'Use when' trigger clause and misses natural synonyms like 'revert'/'rollback'. It answers 'what' well but only weakly implies 'when'.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when reverting Conductor tracks, phases, or tasks.'

Include natural synonyms users say ('revert', 'rollback', 'undo') alongside 'undo' to improve trigger term coverage.

Name 1-2 more concrete actions (e.g. 'creates revert commits and resets task status') to raise specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Names the domain ('Git-aware undo') and concrete work units ('track, phase, or task'), but lists only one action; matches the anchor 'Names domain and 1-2 concrete actions' rather than the multi-action level 4.	3 / 5
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes 'undo' and 'git' but omits common synonyms a user would naturally say such as 'revert' or 'rollback', fitting 'Some relevant keywords but missing common variations or synonyms.'	3 / 5
Distinctiveness Conflict Risk	The Conductor track/phase/task model is a distinct niche with minimal conflict risk, though 'git-aware undo' could overlap slightly with general git-undo skills, fitting 'Mostly distinct; minor overlap risk.'	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/conductor-revert/SKILL.md
Commit: 57c135b

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.