orch-pipeline

Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly. Not usually invoked directly; it applies when an orch-* skill delegates its gated Research-Plan-TDD-Review-Commit pipeline.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/orch-pipeline/SKILL.md

Quality

Content

81%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 tight, well-structured orchestration reference with concrete agent/command mappings, an explicitly gated multi-phase workflow, and a verification checklist; its only weakness is minor redundancy and the option to factor the larger tables into reference files.

Dimension	Reasoning	Score
Conciseness	The body is lean — tables and short bullets, assumes Claude knows the underlying ECC commands — with only minor redundancy between the family-table note and the phase descriptions that could be trimmed.	4 / 5
Actionability	Concrete, executable mappings throughout: named agents ('planner', 'code-reviewer', 'tdd-guide'), commands ('/code-review', '/gan-build "<brief>" --skip-planner'), and flags ('--max-iterations', '--pass-threshold'), with fallbacks per phase; gaps are minor since actual execution is delegated to those tools.	4 / 5
Workflow Clarity	A clearly numbered 0–6 phase sequence with two explicit gates (GATE 1 after Plan, GATE 2 before Commit), a size classifier driving which phases run, feedback loops (build breaks → /build-fix; CRITICAL/HIGH findings resolved before Gate 2), and a final Verification checklist.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one-level-deep, clearly signaled references to repo rules (rules/common/development-workflow.md, security.md, testing.md) and no nested references; at ~115 lines some of the agent/command map could live in a reference file, but placement is reasonable.	4 / 5
	Total	17 / 20 Passed

Description

63%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 is well-scoped and concrete about what the engine contains, with strong distinctiveness, but its trigger terms are architectural jargon rather than natural user phrasing and it contains a duplicated 'Not usually invoked directly' sentence.

Suggestions

Rewrite the trigger clause in user-natural language, e.g. 'Use when an orch-* operation skill (orch-add-feature, orch-fix-defect, ...) needs to run its gated Research→Plan→TDD→Review→Commit pipeline,' so it reads as something a user would actually say.

Remove the duplicated 'Not usually invoked directly.' sentence — the redundancy pads the description and reads as an editing error.

Consider adding concrete operation names (feature, fix, refactor, mvp) as trigger keywords so the skill surfaces when those operation types are requested.

Dimension	Reasoning	Score
Specificity	Lists several concrete components ('the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates'), giving clear coverage of what the engine defines, though these are objects rather than discrete actions.	4 / 5
Completeness	Both 'what' (defines pipeline, classifier, agent map, gates) and 'when' ('it applies when an orch-* skill delegates...') are present and explicit, though the 'when' is a structural delegation trigger rather than a user-facing use case.	4 / 5
Trigger Term Quality	The only triggers are internal jargon ('orch-* skill delegates its gated Research-Plan-TDD-Review-Commit pipeline'); a user would never naturally say these phrases, and common natural-language variations are absent.	2 / 5
Distinctiveness Conflict Risk	A clearly scoped niche ('Shared orchestration engine for the orch-* skill family') with distinct delegation triggers means minimal risk of firing for unrelated skills.	5 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/orch-pipeline/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.