workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

Quality

59%

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/AI-Agents-Safe-Coding-Skills-claude/skills/workflow-patterns/SKILL.md

The canonical home for this skill is workflow-patterns in rmyndharis/antigravity-skills

Quality

Content

43%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 well-structured, concise overview that sets up clean progressive disclosure in form, but the actual guidance is generic and non-executable, the multi-step workflow it governs is never sequenced with validation checkpoints, and its one detailed reference is a dangling path to a missing file.

Suggestions

Add a concrete, sequenced workflow (e.g. 1. read plan.md → 2. write failing test → 3. implement → 4. verify → 5. commit) with an explicit validation/feedback checkpoint before committing.

Replace the generic Instructions bullets with specific, executable guidance — example commit-message format, how to run the verification protocol, what a phase checkpoint requires.

Provide the referenced `resources/implementation-playbook.md` (or remove/fix the dangling reference) so the signaled detailed content is actually reachable.

Dimension	Reasoning	Score
Conciseness	The body is lean, uses short bullet lists, and does not over-explain concepts Claude already knows (no definition of TDD or git); the only trimmable redundancy is the intro paragraph restating the frontmatter description and the generic Instructions bullets.	4 / 5
Actionability	Guidance is high-level and descriptive — "Clarify goals, constraints, and required inputs", "Apply relevant best practices and validate outcomes" — with no concrete commands, code, or specific steps; the only concrete pointer is the playbook reference, which is minimal and (per the bundle listing) points to a missing file.	2 / 5
Workflow Clarity	Despite governing a multi-step TDD/checkpoint/commit/verify workflow, the body never sequences the steps or shows validation checkpoints; the phases are only named in a bullet list, leaving a rough implied sequence with poorly defined steps and no validation feedback loop.	2 / 5
Progressive Disclosure	Sections are well-organized and the single reference to `resources/implementation-playbook.md` is one level deep and clearly signaled in both Instructions and Resources, but the referenced file does not exist in the bundle (no resources/ directory), so navigation leads nowhere.	3 / 5
	Total	11 / 20 Passed

Description

75%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 solid, third-person description that names a clear niche and provides explicit "Use this skill when" trigger guidance with several concrete activities. It is held below top marks by slightly abstract verbs, a few missing synonyms, and a what/when that are intertwined rather than separated.

Suggestions

Lead with a crisp standalone capability statement (the "what") before the "Use this skill when" clause so what and when are clearly separated.

Add common synonyms and concrete file/context triggers users would say, e.g. "commit messages", "plan.md", "red-green-refactor".

Swap the passive verb "understanding the verification protocol" for an action verb like "running the verification protocol".

Dimension	Reasoning	Score
Specificity	Lists several concrete actions tied to the domain — "implementing tasks according to Conductor's TDD workflow", "handling phase checkpoints", "managing git commits for tasks", "understanding the verification protocol" — with only minor coverage gaps (e.g. "understanding" is a state, not an action).	4 / 5
Completeness	The "Use this skill when..." clause gives explicit when-guidance with concrete triggers, and the what is embedded in those activity clauses; both are present but the what is blended into the when rather than stated as a crisp standalone capability, keeping it just below a 5.	4 / 5
Trigger Term Quality	Includes natural terms a Conductor user would say — "TDD workflow", "phase checkpoints", "git commits", "verification protocol" — giving good keyword coverage, though a few common synonyms (e.g. "tests", "commit messages") are absent.	4 / 5
Distinctiveness Conflict Risk	The Conductor-specific niche ("Conductor's TDD workflow", "phase checkpoints", "verification protocol") makes it mostly distinct, though broad terms like "git commits" and "TDD" carry minor overlap risk with generic git/test skills.	4 / 5
	Total	16 / 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/workflow-patterns/SKILL.md
Commit: 900c504

Reviewed: 1 hour 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.