CtrlK
BlogDocsLog inGet started
Tessl Logo

ralphinho-rfc-pipeline

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. Use when running RFC-driven multi-agent execution with quality gates and a merge queue.

59

Quality

69%

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 ./skills/ralphinho-rfc-pipeline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A lean, well-structured overview that lays out a coherent multi-stage orchestration pattern with clear sequencing and merge-queue safeguards. Its chief limitation is actionability: it describes the framework conceptually but stops short of the executable commands, code, or concrete step sequences needed to actually drive the pipeline.

Suggestions

Add concrete, runnable guidance for at least the key transitions, e.g. an example DAG-decomposition prompt or a sample `unit spec` filled in with real values, so Claude can execute rather than only conceptualize.

Make the validation feedback loop explicit in the Quality Pipeline (e.g. '4. tests -> 5. review: if review finds issues, return to step 3') to satisfy the validate-fix-retry pattern the merge/recovery sections already imply.

Specify how outputs are produced or where they are written (e.g. a path or filename convention for the RFC execution log and unit scorecards) so the 'Outputs' section is actionable.

DimensionReasoningScore

Conciseness

The body is short and largely free of padding, assuming Claude's familiarity with concepts like RFCs and merge queues; the only minor over-explanation is the inspirational attribution line that could be trimmed.

4 / 5

Actionability

Guidance is concrete in structure (named pipeline stages, a unit spec template with explicit fields, complexity tiers) but provides no executable commands, code, or exact steps to actually run the pipeline, leaving it as a high-level framework rather than a runnable recipe.

3 / 5

Workflow Clarity

The pipeline and per-unit quality stages are clearly sequenced, and the merge-queue and recovery sections include validation-like rules ('Never merge a unit with unresolved dependency failures', 're-run integration tests after each queued merge'), though explicit validate-then-fix feedback loops are implied rather than spelled out.

4 / 5

Progressive Disclosure

For a sub-50-line skill with no external bundle files, the content is well-organized into clear single-level sections (Pipeline Stages, Unit Spec Template, Complexity Tiers, Quality Pipeline, Merge Queue Rules, Recovery, Outputs) making it easy to navigate with no nested references.

5 / 5

Total

16

/

20

Passed

Description

67%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 solid, third-person description that conveys both the skill's purpose and a use trigger, with several concrete capabilities named. Its main weakness is that the trigger language leans on specialized jargon and restates the capability list rather than offering natural, varied user-facing phrases.

Suggestions

Rewrite the 'Use when...' clause with natural trigger phrases a user would say, e.g. 'Use when a feature is too large for one agent and needs to be split into independently verifiable work units with a merge queue'.

Add everyday synonyms alongside the jargon (e.g. 'splitting a large feature into subtasks', 'coordinating multiple agents', 'dependency-ordered work units') to broaden trigger coverage.

Differentiate the 'what' and the 'when' so the trigger clause adds new information rather than repeating the capability list.

DimensionReasoningScore

Specificity

The description names the domain and lists several specific concrete actions ('DAG decomposition', 'unit assignment', 'unit validation', 'merge queue', 'work unit orchestration') rather than vague abstractions, with only minor coverage gaps.

4 / 5

Completeness

It states both what it does (RFC-driven multi-agent DAG execution with quality gates) and when to use it ('Use when running RFC-driven multi-agent execution...'), though the 'when' largely restates the 'what' rather than giving distinct concrete trigger phrases.

4 / 5

Trigger Term Quality

Trigger terms ('RFC-driven multi-agent execution', 'quality gates', 'merge queue') are domain-relevant but rely on niche jargon rather than the natural phrases a user would actually say, missing common synonyms or variations.

3 / 5

Distinctiveness Conflict Risk

The RFC/DAG/merge-queue framing carves a fairly distinct niche with limited overlap risk against generic coding skills, though the multi-agent orchestration space has some adjacent skills that could partially overlap.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.