conductor-revert

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

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 ./skills/conductor-revert/SKILL.md

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 an unusually strong operational skill: fully executable git commands, exact interactive templates, explicit confirmation gates, and thorough edge-case handling for a risky destructive workflow. Its weaknesses are generic boilerplate sections that pad the token budget and a dangling reference to a nonexistent `resources/implementation-playbook.md` that undermines progressive disclosure.

Suggestions

Remove the generic "Use this skill when", "Do not use this skill when", "Instructions", and "Limitations" filler sections — they add tokens without operational value.

Fix or remove the `resources/implementation-playbook.md` reference: the file does not exist in the bundle, so the pointer is broken.

Consider moving the long ASCII display templates (execution plan, conflict, verification banners) into a reference file to slim the main SKILL.md, keeping only the behavioral rules inline.

Dimension	Reasoning	Score
Conciseness	The operational core (commands, menus, safety rules) is dense and earns its tokens, but the "Use this skill when", "Do not use this skill when", "Instructions" ("Clarify goals, constraints, and required inputs. Apply relevant best practices"), and "Limitations" sections are generic template filler Claude does not need. It is above the verbosity of anchor 2 (no concept re-teaching) but has several sections that should be trimmed, matching anchor 3.	3 / 5
Actionability	The guidance is fully executable: exact commands like `git log --oneline --grep="{trackId}" --grep="Task {X.Y}" --all-match`, `git revert --no-edit {sha}`, copy-paste menu and execution-plan templates, concrete examples (`auth_20250115:phase2`), and explicit plan.md/metadata update steps cover the common task, phase, and track cases.	5 / 5
Workflow Clarity	A destructive batch operation is sequenced end-to-end (pre-flight checks → target selection → commit discovery → plan display → explicit 'YES' confirmation → ordered execution → conflict halt → plan.md update → verification), with explicit validation checkpoints, a halt-on-conflict feedback loop, and a Safety Rules checklist. This matches the anchor with validation steps, feedback loops, and checklists.	5 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a ~370-line monolith and its only reference — "open `resources/implementation-playbook.md`" — points to a file that does not exist (no references/, scripts/, assets/, or resources/ directories are present). Structure is present but the single reference is dangling and unverified, matching anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

50%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 states a clear 'what' with useful scope granularity, but it entirely lacks a 'when to use' trigger clause and omits the word "revert" that both the skill name and users' natural language would use. It reads as a terse capability label rather than a trigger-rich description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to revert, undo, or roll back work in a Conductor track, phase, or task."

Use the natural verb "revert" (matching the skill name) and include synonyms like "undo" and "roll back" so trigger matching works across phrasings.

Name one or two concrete actions (e.g. "creates git revert commits per work unit and resets plan.md task status") to raise specificity.

Dimension	Reasoning	Score
Specificity	"Git-aware undo by logical work unit (track, phase, or task)" names the domain (git undo) and the three granularity levels, but the only action named is the generic "undo" — it does not list concrete actions like revert, commit discovery, or plan restoration, so it is not comprehensive (not a 4).	3 / 5
Completeness	The 'what' is clearly stated ("Git-aware undo by logical work unit"), but there is no 'Use when...' clause or equivalent trigger guidance at all, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Git" and "undo" are natural terms users would say, and "track, phase, task" match the conductor vocabulary, but common synonyms like "revert", "rollback", or "unwind" are missing even though the skill is named conductor-revert — some relevant keywords, missing variations.	3 / 5
Distinctiveness Conflict Risk	The "(track, phase, or task)" qualifier ties it to the conductor framework, but the description never mentions Conductor and "Git-aware undo" could overlap with any general git-revert/undo skill a user might invoke, so it sits at 'somewhat specific but could still overlap'.	3 / 5
	Total	12 / 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: sickn33/agentic-awesome-skills
Path: skills/conductor-revert/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.