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.

1.75x

Quality

—

Does it follow best practices?

Impact

100%

1.75x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with strong, well-sequenced workflows and explicit validation gates. Its weaknesses are token inefficiency from restating generic engineering knowledge and a monolithic structure with no progressive disclosure via referenced files.

Suggestions

Move generic QA-gate, security-audit, and best-practices content (much of which Claude already knows) into a separate reference file or trim to only Conductor-specific essentials, keeping the body lean.

Split the large body into referenced files (e.g., references/qa-gates.md, references/deviations.md, references/error-recovery.md) with clearly signaled one-level-deep links so SKILL.md serves as a concise overview.

Consolidate the repeated commit/git-notes/checkpoint command patterns into a single referenceable example rather than restating the format across multiple sections.

Dimension	Reasoning	Score
Conciseness	The Conductor-specific material (status markers [ ]/[~]/[x], commit footers with Task/Track, git notes, checkpoint SHAs) is efficient, but large stretches of the QA gates, security audit, performance, and 12-item Best Practices sections restate generic software-engineering knowledge Claude already has. It is not score 1 because it avoids explaining basic concepts, and not score 3 because substantial generic padding could be trimmed.	2 / 3
Actionability	Provides copy-paste-ready, executable guidance throughout: pytest/ruff/mypy commands, git commit and git notes commands with full message templates, and concrete plan.md markdown snippets with exact status markers. It is not score 2 because the examples are complete and executable rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	The 11-step TDD lifecycle is clearly sequenced with explicit validation gates (RED must fail, GREEN must pass, 80% coverage check) and feedback loops ("Do NOT proceed to REFACTOR" on failure, "Do NOT proceed without explicit approval", the error-recovery section). It is not score 2 because validation checkpoints and recovery loops are explicit rather than implicit.	3 / 3
Progressive Disclosure	The body is well-organized with clear section headers, but it is a single monolithic file with no bundle/reference files, and content that could be split (QA gates, deviations, TDD variations, error recovery) is all inline. It is not score 1 because structure and navigation are present, and not score 3 because no one-level-deep references exist and the file is far too long to count as a concise overview.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 has a clear niche and concrete, specific activities with an explicit trigger clause. Its main weaknesses are jargon-heavy trigger terms and a blended what/when structure that does not cleanly separate capabilities from triggers.

Suggestions

Add natural-language trigger variations a user might actually say (e.g., "writing tests", "committing work", "phase review") alongside the Conductor-specific terms to broaden trigger matching.

Lead with a concise capability statement (what it does), then add a separate "Use when..." clause so the "what" and "when" are clearly distinguished rather than folded into one phrase.

Soften jargon like "verification protocol" and "phase checkpoints" with plainer equivalents so the description reads as user-facing rather than system-internal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "implementing tasks according to Conductor's TDD workflow", "handling phase checkpoints", "managing git commits for tasks", "understanding the verification protocol" — matching the score-3 anchor of several specific concrete actions. It is not score 2 because it goes beyond naming a domain to enumerating four distinct activities.	3 / 3
Completeness	An explicit "Use this skill when" trigger is present, but the four phrases serve as both the capability statement and the trigger, so the distinct "what does this do" is implied rather than cleanly separated from "when". It is not score 3 because the what and when are not clearly distinguished as in the reference example, and not score 1 because an explicit trigger clause and concrete capabilities are present.	2 / 3
Trigger Term Quality	Relevant terms like "TDD workflow" and "git commits" are natural, but "phase checkpoints" and "verification protocol" are Conductor-specific jargon with limited common-user variation. It is not score 3 because coverage of natural phrasings a user would say is uneven, and not score 1 because several terms are genuinely user-facing.	2 / 3
Distinctiveness Conflict Risk	Anchored to a specific named system ("Conductor's TDD workflow") and a distinctive protocol (phase checkpoints, git notes, verification), giving it a clear niche unlikely to conflict with other skills. It is not score 2 because the Conductor-specific framing makes overlap with generic skills unlikely.	3 / 3
	Total	10 / 12 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
skill_md_line_count	SKILL.md is long (624 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 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.