flow-parallel

Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates

Quality

58%

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/flow-parallel/SKILL.md

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 content is highly actionable and exceptionally well-sequenced, with validation gates and error-recovery loops at every stage of the orchestration. However, it is significantly over-padded with repeated enforcement framing, and it is a monolithic single file that inlines scripts which belong in a scripts/ bundle while also referencing a host-adapter file that does not exist in this bundle.

Suggestions

Cut the redundant enforcement framing: drop the "STOP - SKILL ALREADY LOADED" banner, the "EXECUTION CONTRACT" preamble, and consolidate the per-step "DO NOT PROCEED" lines into the final Prohibitions section — this could remove ~100 lines without losing information.

Move the launch.sh template, dependency-validation Python, and wave-monitor loop into scripts/ files (e.g. scripts/launch-wp.sh, scripts/validate-wbs.py, scripts/run-waves.sh) and reference them, rather than inlining ~300 lines of shell in SKILL.md.

Fix or remove the reference to skills/blocks/codex-host-adapter.md — the file does not exist in this bundle — and define $WP_COUNT in Step 7 (Step 5 only defines lowercase wp_count), which would otherwise break the aggregation loop.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded: every step repeats MANDATORY / "DO NOT PROCEED" framing, a "STOP - SKILL ALREADY LOADED" banner, an ASCII activation banner, and a closing Prohibitions list that restates the per-step gates verbatim — several sections add emphasis rather than information Claude needs.	2 / 5
Actionability	Nearly every step ships copy-paste-ready bash/python (WBS heredoc, dependency cycle detection, launch.sh, wave monitor loop), with only minor gaps: `$WP_COUNT` in Step 7 is never defined (Step 5 sets lowercase `wp_count`), and `<absolute-project-root-path>` is a template placeholder the model must fill.	4 / 5
Workflow Clarity	A strict 7-step sequence with a named validation gate per step (wbs_generated, instructions_written, processes_launched, all_work_packages_complete), explicit failure feedback loops (invalid JSON → stop, dependency cycle → stop, timeout → report and offer retry/kill), and a prohibitions checklist — matching the anchor of clear sequence with explicit validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	Section structure is clear, but the skill is a ~780-line monolith: large executable scripts (launch.sh, the wave monitor, the dependency validator) that belong in scripts/ are fully inlined, and the body references skills/blocks/codex-host-adapter.md which is not present in this bundle (references/, scripts/, assets/ are all absent).	3 / 5
	Total	14 / 20 Passed

Description

53%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 states a clear and reasonably specific capability, but it omits any "Use when..." trigger guidance, which both caps completeness and weakens its usefulness for automatic skill selection. Trigger-term coverage is adequate but lacks synonyms and natural variations. It is mostly distinguishable from sibling planning/orchestration skills.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to parallelize a large task, run a big migration in parallel, or fix multiple issues at once."

Replace the vague "with quality gates" with concrete gate language, e.g. "with per-step validation (WBS checks, dependency cycle detection, exit-code verification)".

Add natural synonyms users would say, such as "parallelize", "split into work packages", or "fan out" to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("large changes, migrations, or multi-issue fixes") and 1-2 concrete actions ("Decompose and execute... in parallel"), but "quality gates" is vague and coverage of what the skill actually does is not comprehensive — matching the anchor-3 example of domain plus 1-2 concrete actions.	3 / 5
Completeness	It has a clear "what" (decompose and execute compound tasks in parallel with quality gates) but no "Use when..." clause or equivalent trigger guidance, which the judging guidelines explicitly cap at 3.	3 / 5
Trigger Term Quality	Terms like "migrations", "multi-issue fixes", and "in parallel" are phrases users would naturally say, but common variations and synonyms (e.g. "parallelize", "split this work up", "fan out") are missing, fitting the anchor of some relevant keywords without full coverage.	3 / 5
Distinctiveness Conflict Risk	"Decompose and execute... in parallel with quality gates" carves a fairly distinct orchestration niche, but it could still overlap with other planning, batch, or code-review skills since the trigger terms are broad, so it is mostly distinct with minor overlap risk rather than a clear unique niche.	4 / 5
	Total	13 / 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
skill_md_line_count	SKILL.md is long (788 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/flow-parallel/SKILL.md
Commit: 0093dab

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.