CtrlK
BlogDocsLog inGet started
Tessl Logo

ccw

Intelligent coordinator — classify intent via structured extraction (action × object × style), map to skill chain, execute wave-by-wave via spawn_agents_on_csv. Barrier skills trigger coordinator-side artifact analysis between waves to dynamically assemble subsequent skill_call args. Each wave can be 1 or N parallel tasks.

49

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/ccw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 dense, highly actionable orchestration spec with a clearly sequenced wave loop, explicit failure handling, and resume support — its main weaknesses are redundancy (barrier skills and routing specified multiple times) and a fully monolithic structure with no reference files despite its length.

Suggestions

Deduplicate: define the barrier-skill set once (e.g. in BARRIER_SKILLS) and derive the Barrier Skills table and [B] chain markers from it, rather than listing them three times.

Move the action/object/style enums, the chain-definitions table, and the 40-item skill inventory into references files (e.g. references/chain-map.md), keeping SKILL.md as a lean overview with clearly signaled links.

Specify the undefined pieces the loop depends on: the complexity-assessment criteria (what makes a feature 'low' vs 'high'), the readCSV helper, and how WAVE_INSTRUCTION placeholders are bound per row.

DimensionReasoningScore

Conciseness

The ~675-line body avoids explaining known concepts, but barrier skills are enumerated three times (Barrier Skills table, [B] markers in Chain Definitions, and the BARRIER_SKILLS set), routing appears as both the detectTaskType code and the chain-definitions table, and a 40-item skill inventory is inlined — mostly efficient but with clear tightening opportunities, fitting anchor 3.

3 / 5

Actionability

Near copy-paste ready: concrete spawn_agents_on_csv invocation with parameters, wave CSV writing code, exact instruction template with report JSON, and CSV schemas. Minor gaps — readCSV, the complexity-assessment criteria, and WAVE_INSTRUCTION binding are referenced but undefined — keep it at anchor 4 rather than 5.

4 / 5

Workflow Clarity

The wave loop is fully sequenced with explicit checkpoints (read results, abort on failure, error table E001–E005 with recovery actions, E004 retry-once, --continue resume), satisfying batch-operation validation. The undefined complexity-assessment step feeding feature (low)/(high) chain selection is a minor gap, so anchor 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist and all content — action/object/style enums, chain-definition tables, skill inventory, barrier analysis code, CSV schemas — is inlined in a single 675-line file. Section headers make it navigable (not anchor 2), but content that clearly belongs in reference files is inline with zero external references, fitting anchor 3.

3 / 5

Total

14

/

20

Passed

Description

47%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 concretely describes the skill's mechanics, but it is written in internal jargon for implementers rather than natural trigger language for users, and it omits any 'when to use' guidance. It functions as a spec summary more than a triggerable skill description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to coordinate, orchestrate, or chain multiple development skills, or wants parallel wave-based execution of a multi-step workflow.'

Replace or gloss internal jargon ('spawn_agents_on_csv', 'barrier skills', 'skill_call args') with user-facing terms like 'parallel sub-agents' and 'planning skills that gate later steps'.

Briefly mention user-visible capabilities beyond the core loop — dry-run preview, session resume via --continue, and the final completion report — so the 'what' is comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'classify intent via structured extraction (action × object × style)', 'map to skill chain', 'execute wave-by-wave via spawn_agents_on_csv', 'coordinator-side artifact analysis' — but coverage has minor gaps (reporting, resume, dry-run unmentioned) and actions lean on internal jargon, fitting anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear (classify intent, map to chain, execute wave-by-wave), but there is no 'Use when…' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Keywords are internal implementation terms ('structured extraction', 'spawn_agents_on_csv', 'barrier skills', 'skill_call args') rather than natural phrases a user would say when needing this skill; only 'coordinator' and 'intent' offer any natural footing, matching anchor 2.

2 / 5

Distinctiveness Conflict Risk

The wave/barrier orchestration mechanism is a distinct niche, but the described scope — routing any development intent to a broad skill inventory — overlaps with many other workflow and orchestration skills, fitting anchor 3.

3 / 5

Total

12

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (675 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
catlog22/Claude-Code-Workflow
Reviewed

Table of Contents

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.