CtrlK
BlogDocsLog inGet started
Tessl Logo

bump-libdatadog

Update/bump the libdatadog native library version in dd-trace-dotnet. Use when the user asks to bump, update, or upgrade libdatadog, or mentions a new libdatadog release version.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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 highly actionable, well-structured procedural skill with concrete commands, a real helper script, and explicit validation checkpoints for a batch operation. The main weakness is mild redundancy in the closing 'Important Notes' section.

Suggestions

Remove or trim the 'Important Notes' section — its SHA-256/SHA-512 and v-prefix points already appear in the version-scheme table and Step 5, so it reads as repetition.

Consider condensing 'Related Files (no changes needed, but useful context)' to the two or three files most likely to matter during a bump, rather than listing six.

DimensionReasoningScore

Conciseness

The body is mostly efficient and focused on specialized knowledge Claude lacks (version scheme, reduced feature set, glibc caps), but the 'Important Notes' section restates the SHA-256/SHA-512 and v-prefix facts already covered by the table and steps — minor trimming opportunity. Not a 3 because the bulk earns its place; not a 5 because of the noticeable redundancy.

4 / 5

Actionability

Provides copy-paste-ready commands (the fetch-release-hashes.sh script invocation, Nuke build targets) and exact file paths and values to update, covering the common bump case fully and executably.

5 / 5

Workflow Clarity

A clear 6-step sequence with an explicit verification step (confirm 8 hashes, confirm version strings match, run build targets) and a feedback loop for hash mismatches — a checklist for this batch operation.

5 / 5

Progressive Disclosure

Well-organized sections with a single one-level-deep bundle reference (scripts/fetch-release-hashes.sh, which exists and is clearly signaled inline); content is appropriately placed in SKILL.md with no nested reference chains.

5 / 5

Total

19

/

20

Passed

Description

90%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 tight, well-formed description that clearly states the task and its trigger conditions with natural user phrasing. Its only limitation is that it describes a single action, so specificity is solid rather than comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('libdatadog native library version in dd-trace-dotnet') and a single concrete action ('Update/bump'), which matches the anchor for naming the domain with 1-2 concrete actions but not comprehensive coverage.

3 / 5

Completeness

Explicitly states both what ('Update/bump the libdatadog native library version in dd-trace-dotnet') and when ('Use when the user asks to bump, update, or upgrade libdatadog...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural synonyms users would say — 'bump, update, or upgrade libdatadog' — plus 'mentions a new libdatadog release version', giving comprehensive trigger coverage for this domain.

5 / 5

Distinctiveness Conflict Risk

Targets a highly specific niche (bumping libdatadog in dd-trace-dotnet) with distinct triggers, making conflict with other skills minimal.

5 / 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
DataDog/dd-trace-dotnet
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.