CtrlK
BlogDocsLog inGet started
Tessl Logo

risk-register

Maintain docs/RISK_REGISTER.md, the living, append-only list of every deferred item, interim shortcut, and open architecture decision for this project. Use when a shortcut is taken, a decision is postponed, a follow-up is filed, or an existing entry is actually resolved. DO NOT use for accepted, finalized architecture decisions (use adr-capture instead), for session-local working notes that don't need to survive across the team (use context-file / the local scratch-notes directory instead), or for anything that must stay confidential (the register is a committed, team-visible doc). Triggers: 'add to risk register', 'log this as a risk', 'track this shortcut', 'this is a known gap', 'mark risk #N resolved', 'what's on the risk register', 'what's still open'.

75

Quality

93%

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

92%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 strong, dense instruction-only skill body: every section carries non-obvious project convention, workflows are sequenced with explicit validation checkpoints and recovery paths, and detail is correctly split into two clearly signaled reference files and four bundle assets that all exist. The only cost is token overhead from restating the append-only and .context/ rules across multiple sections and a slightly philosophical Mindset section.

DimensionReasoningScore

Conciseness

Nearly all content is project-specific convention Claude cannot know (row schema, append-only rules, .context/ prohibition, validator semantics) with no padding explaining known concepts, but the append-only and .context/ rules are restated across Prerequisites, Workflow, Anti-Patterns and Troubleshooting, and the Mindset section carries philosophical prose ('An unenforced rule that's actually followed is worth more here...') that could be trimmed — efficient with minor over-explanation, not the lean top anchor.

4 / 5

Actionability

Fully executable guidance throughout: exact file paths, copy-paste commands ('scripts/validate-risk-register-append-only.sh', 'scripts/validate-risk-register-schema.sh') with expected output and exit codes on success and failure, a fully specified column table with enums and date formats, and a troubleshooting table mapping each error to a specific fix.

5 / 5

Workflow Clarity

Both add and resolve workflows are numbered with explicit validation steps ('Run both validation scripts and confirm each prints no error output and exits 0 before committing'), a Definition of Done checklist, and error-recovery feedback loops in Troubleshooting ('fix and re-run before committing', 'update validate-risk-register-schema.sh's expected_fields') — a clear match to the top anchor.

5 / 5

Progressive Disclosure

The body is a well-organized overview with a References table giving topic, path, and 'When to Use' for two one-level-deep reference files (both verified to exist in the bundle), plus correctly placed template/schema/script assets; not below 5 because no content that belongs in a separate file is inlined and no reference is nested.

5 / 5

Total

19

/

20

Passed

Description

95%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.

An exemplary description: it states the exact artifact and its nature, gives explicit use and do-not-use conditions with sibling-skill routing, and closes with natural trigger phrases in third person. The only nit is that concrete row-level operations are implied via triggers rather than declared as capabilities.

DimensionReasoningScore

Specificity

Names the concrete artifact ('docs/RISK_REGISTER.md, the living, append-only list of every deferred item, interim shortcut, and open architecture decision') and the add/resolve operations, but the operations are conveyed through use-conditions and trigger phrases rather than stated as explicit capability actions, leaving a minor coverage gap versus the comprehensive anchor.

4 / 5

Completeness

Explicitly answers what ('Maintain docs/RISK_REGISTER.md, the living, append-only list...'), when ('Use when a shortcut is taken, a decision is postponed, a follow-up is filed, or an existing entry is actually resolved'), when not (three DO-NOT clauses), and includes concrete trigger phrases — a clear match to the top anchor.

5 / 5

Trigger Term Quality

An explicit Triggers list gives natural phrases a user would actually say ('add to risk register', 'log this as a risk', 'track this shortcut', 'this is a known gap', 'mark risk #N resolved', 'what's still open') plus synonyms for both querying and mutating the register; not below 5 since no common variation is missing, and not above because 5 is the scale maximum.

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit routing away from the nearest neighbors ('use adr-capture instead', 'use context-file / the local scratch-notes directory instead') and distinct, register-specific triggers; minimal conflict risk.

5 / 5

Total

19

/

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

referenced_paths_exist

Referenced path issues: 3 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
pantheon-org/tekhne
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.