update-knowledge-base
Cross-reference recently shipped tickets against your help center and changelog to detect outdated articles, missing documentation, and undocumented features. Suggests updates and writes draft copy where possible. Use after each release or on a weekly cadence.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./execution-skills/skills/update-knowledge-base/SKILL.mdQuality
Discovery
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.
This is a strong description that clearly articulates a specific, well-scoped capability with explicit temporal triggers for when to use it. The main weakness is that trigger terms could be broader to capture more natural user language variations (e.g., 'docs', 'knowledge base', 'support articles'). Overall it reads as professional, concrete, and distinctive.
Suggestions
Add common user-facing synonyms like 'docs', 'knowledge base', 'support articles', 'FAQ', 'release notes' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: cross-referencing shipped tickets against help center and changelog, detecting outdated articles, detecting missing documentation, detecting undocumented features, suggesting updates, and writing draft copy. | 3 / 3 |
Completeness | Clearly answers both 'what' (cross-reference tickets against help center/changelog to detect gaps, suggest updates, write drafts) and 'when' ('Use after each release or on a weekly cadence'). The 'when' clause is explicit with clear temporal triggers. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'help center', 'changelog', 'shipped tickets', 'outdated articles', 'missing documentation', 'undocumented features', and 'release'. However, it misses common user variations like 'docs', 'knowledge base', 'support articles', 'FAQ', or 'release notes' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche at the intersection of release management and documentation maintenance. The specific combination of cross-referencing shipped tickets against help center content is highly distinctive and unlikely to conflict with general documentation or ticket management skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable workflow template for detecting documentation gaps after releases, with clear steps and useful placeholder variables. Its main weaknesses are the lack of validation checkpoints in the workflow, the absence of concrete executable commands (relying on implicit MCP usage), and some unnecessary introductory prose. The structure is adequate but could benefit from explicit verification steps and more actionable MCP-specific instructions.
Suggestions
Add explicit validation checkpoints, e.g., after Step 1 verify ticket count is non-zero, after Step 2 confirm docs were successfully fetched, and after Step 5 verify the output file was saved and return a confirmation.
Include concrete MCP tool call examples (e.g., specific Linear/Jira query syntax, Google Drive file creation commands) instead of relying on Claude to infer the right tool usage.
Trim the introductory paragraph — the description already conveys the purpose; jump straight into the prompt template or setup.
Add an example output snippet showing what a completed DocUpdates file looks like, so Claude has a concrete target format.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph ('Every release creates documentation debt...') is somewhat redundant with the description and could be trimmed. The prompt template itself is reasonably lean, but the introductory framing adds tokens without new information for Claude. | 2 / 3 |
Actionability | The skill provides a structured prompt template with clear steps and placeholder variables, which is helpful. However, it lacks executable code or concrete commands — it's more of a workflow outline with template variables than copy-paste-ready instructions. The output format is specified but the actual mechanism (MCP calls, file creation commands) is left implicit. | 2 / 3 |
Workflow Clarity | The five steps are clearly sequenced and logically ordered. However, there are no validation checkpoints — no step to verify that ticket sources were read correctly, that documentation URLs are accessible, or that the output file was successfully saved. For a workflow involving cross-referencing multiple data sources, a verification step would be important. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections (prompt template, setup, placeholders, tips) which is good. However, everything is in a single file with no references to supporting materials. The prompt template section is quite long and could benefit from being separated, and there are no bundle files to support more detailed guidance on gap detection heuristics or output formatting. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.