pipeline

End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".

Quality

81%

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

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 body is well-sequenced with strong validation checkpoints and concrete, executable orchestration commands. Its main gaps are verbosity from duplicated invocation/report templates and a monolithic structure with no progressive disclosure despite exceeding the simple-skill line count.

Suggestions

Collapse the duplicated "How to invoke" blocks: pick the preferred form (slash-command or Task tool) and reference the alternative once instead of repeating both per phase.

Move the large final-report and RALPH HANDOFF templates into a references/ file (e.g. REPORT_TEMPLATES.md) and link to it, improving progressive disclosure and trimming the main body.

Tighten the repeated progress-report snippets into one parameterized template referenced from each phase rather than restating the format.

Dimension	Reasoning	Score
Conciseness	The ~190-line body avoids explaining concepts Claude already knows, but is padded by duplicated invocation forms (slash-command plus Task-tool variants) and repeated report/handoff templates that could be tightened; it is mostly efficient but not lean.	2 / 3
Actionability	Provides concrete, runnable command forms throughout — "/ralph 1 --batch {batch_id} --type extract", Task-tool call templates, and "/archive-batch {batch_id}" — with specific placeholders rather than pseudocode, matching the copy-paste-ready anchor for an orchestration skill.	3 / 3
Workflow Clarity	A clear six-phase sequence with an ASCII flow diagram and explicit validation checkpoints for this batch operation ("Do NOT proceed to archive" when tasks remain, verify-all-done-before-archive, per-phase failure handling and a resumability table) meets the explicit-validation-and-feedback-loops anchor.	3 / 3
Progressive Disclosure	The skill is monolithic: no references/, scripts/, or assets/ bundle exists and all detail (report templates, handoff block, resumability table) is inline in a ~190-line SKILL.md, so structure is present but content that should be split out is not, fitting the mid anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 strong: it names concrete phases, answers both what and when with explicit triggers, and occupies a distinct orchestration niche. Its only weakness is a narrow, command-leaning trigger set that could add more natural user phrasings.

Suggestions

Broaden trigger terms beyond slash commands with more natural variations a user would say unprompted, e.g. "run the whole pipeline on this", "process this source from start to finish".

Keep the concise action list but consider noting the input shape (a source file path) earlier so the what/when pairing is immediately grounded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — "seed, reduce, process all claims through reflect/reweave/verify, archive" — matching the anchor for several specific concrete actions rather than a vague domain label.	3 / 3
Completeness	Explicitly answers both what ("End-to-end source processing ... The full pipeline in one command") and when ("Triggers on /pipeline ... process this end to end, full pipeline"), satisfying the explicit-trigger bar for the top anchor.	3 / 3
Trigger Term Quality	Includes some natural triggers ("process this end to end", "full pipeline") alongside slash-command forms, but the set is small and command-centric, missing common phrasings a user might naturally say.	2 / 3
Distinctiveness Conflict Risk	Carves a clear niche as the end-to-end wrapper with its own /pipeline trigger, distinct from the sibling /seed, /ralph, /reduce skills it orchestrates, making wrong-skill conflict unlikely.	3 / 3
	Total	11 / 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
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	14 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/pipeline/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.