CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rca

Conduct a root-cause analysis on a bug, incident, or regression — reproduce the failure, reconstruct the timeline, run a 5-whys chain, distinguish symptom from proximate cause from root cause, sweep for siblings, and propose a fix that addresses the cause (not the symptom). Use when the user says "/rca", "root cause", "5 whys", "why is this failing", "investigate this regression", or after any failure the team wants to learn from rather than just patch.

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

Excellent instructional content: a dense, fully prescriptive 11-step workflow with built-in validation gates and a restoring checklist, concrete output formats, and well-organized one-level-deep bundle references that were verified to exist. Nothing explains what Claude already knows, and every rule is task-specific.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no general concepts (what git or 5-whys is) are explained, and all detail is deferred to bundle files read at named steps. Every line states a task-specific rule ("A bug you cannot trigger is a story", "Undoing the artifact does not un-notify anyone") that earns its place, matching anchor 5 rather than the trimmable over-explanation of anchor 4.

5 / 5

Actionability

Concrete commands are given where they exist ("git status --porcelain", "git worktree add ...", "<plugin root>/scripts/prose-lint.py") and each step specifies the exact artifact and format to produce (**Answer**/**Evidence**, **How validated**/**Result**, counterfactual verdict labels with defined semantics). Per the rubric's code-vs-instruction note, an instruction-only skill with this specificity of guidance merits the top anchor.

5 / 5

Workflow Clarity

Eleven clearly sequenced steps with pervasive explicit validation checkpoints: an UNVERIFIED link "supports nothing below it", "Unconfirmed means the RCA is not done", and a Definition of Done whose items "send you back to the step that produces it" — a genuine feedback loop. This matches the anchor-5 pattern (validate → fix → retry) rather than the minor validation gaps of anchor 4.

5 / 5

Progressive Disclosure

The body is an overview that splits detail into one-level-deep references, all of which exist and whose cited sections match (chain.md § 4/5/7, fix.md § 8–11, rationalizations.md). The references table signals what each file holds and exactly when to read it, making navigation trivial — a clean anchor-5 match.

5 / 5

Total

20

/

20

Passed

Description

88%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 strong description: it specifies the full RCA capability set concretely, gives explicit 'Use when' triggers with natural quoted phrasings, and carves out a distinct niche. The only gaps are a few missing synonyms (e.g., "postmortem") and slight trigger overlap with generic debugging requests.

DimensionReasoningScore

Specificity

The description lists six-plus concrete actions — "reproduce the failure, reconstruct the timeline, run a 5-whys chain, distinguish symptom from proximate cause from root cause, sweep for siblings, and propose a fix" — giving comprehensive coverage of the RCA domain. It exceeds anchor 4 because no meaningful capability gaps remain uncovered.

5 / 5

Completeness

Explicitly answers both questions: what (the full concrete action list) and when ("Use when the user says ... or after any failure the team wants to learn from rather than just patch") with concrete trigger phrases. This is a direct match for the anchor-5 example pattern, not merely the looser 'when' of anchor 4.

5 / 5

Trigger Term Quality

Includes natural quoted phrases users would say — "/rca", "root cause", "5 whys", "why is this failing", "investigate this regression" — plus the intent cue "after any failure the team wants to learn from rather than just patch". It falls short of anchor 5's comprehensive synonym coverage because common terms like "postmortem" and "post-incident review" are absent.

4 / 5

Distinctiveness Conflict Risk

A clear RCA niche with distinct triggers ("5 whys", "/rca", sibling sweep), but the trigger "why is this failing" could also fire on ordinary debugging requests — minor overlap with closely related debugging skills per anchor 4 rather than the minimal conflict risk of anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

korya/swd-skills

Path

skills/rca/SKILL.md

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.