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

70%

Does it follow best practices?

Impact

100%

1.75x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/workflow-patterns/SKILL.md

The canonical home for this skill is workflow-patterns in wshobson/agents

Quality

Content

62%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 delivers a clear, well-validated workflow with strong actionability, but it is a verbose monolith that repeats checkpoint material and explains concepts Claude already knows, and it makes no use of progressive disclosure despite being far over the simple-skill threshold.

Suggestions

Collapse the three checkpoint explanations (Phase Completion Protocol, Verification Checkpoints, Checkpoint Verification Details) into a single section and trim the restating Best Practices list to remove redundancy.

Delete Claude-known primer content (TDD red-green-refactor explanation, conventional commit format tutorial, fixtures/mocks/atomic-commits advice) and keep only Conductor-specific conventions.

Move reference-style material (QA gates, Git Integration format reference, TDD Variations by Task Type) into separate files under references/ and link to them from a concise overview so SKILL.md stays a lean entry point.

Dimension	Reasoning	Score
Conciseness	The ~620-line body restates checkpoints three times (Phase Completion Protocol, Verification Checkpoints, Checkpoint Verification Details), includes a 12-item Best Practices section that re-prior summarizes earlier content, and explains Claude-known concepts (red-green-refactor, conventional commit format, fixtures/mocks, atomic commits), making it noticeably padded.	2 / 5
Actionability	Provides mostly executable guidance — concrete pytest/git commands, a complete email-validation commit example, git notes templates, and plan.md markdown formats — with only minor gaps where commands carry placeholders like <last-checkpoint-sha> or illustrative SHAs.	4 / 5
Workflow Clarity	The 11-step TDD lifecycle is clearly sequenced with explicit validation gates (tests pass, coverage >= 80%, full-suite run), a hard "Do NOT proceed without explicit approval" checkpoint, an Error Recovery section supplying feedback loops, and manual-verification checklists.	5 / 5
Progressive Disclosure	Section headers organize the monolith well, but no bundle files exist and all content — including reference-style material (QA gates, Git Integration, checkpoint details, TDD variations) that would suit separate files — is inlined in SKILL.md with no one-level-deep navigation.	3 / 5
	Total	14 / 20 Passed

Description

78%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 strong, domain-specific description that names concrete actions and includes an explicit trigger clause, with only minor room to sharpen the when-triggers and convert the abstract "understanding" action into something more concrete.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions tied to a named domain — "implementing tasks according to Conductor's TDD workflow", "handling phase checkpoints", "managing git commits for tasks", "understanding the verification protocol" — though "understanding" is less of a concrete doing-action, leaving minor gaps that keep it below a 5.	4 / 5
Completeness	Both what and when are present via the explicit "Use this skill when..." clause, but the triggers are framed as activities rather than user utterances (e.g., "when the user asks to..."), so the when could be more explicit.	4 / 5
Trigger Term Quality	Good keyword coverage with natural terms a Conductor user would say ("TDD workflow", "git commits", "verification"), though some terms like "phase checkpoints" and "verification protocol" lean toward domain jargon with a few common synonyms missing.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche around "Conductor's TDD workflow" with distinctive triggers (phase checkpoints, task-scoped git commits, verification protocol), giving it minimal conflict risk with unrelated skills.	5 / 5
	Total	17 / 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
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
Path: tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/workflow-patterns/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.