feat: improve aiconfig-projects skill score (47% → 90%)#57
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @nieblara 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | aiconfig-projects | 47% | 90% | **+43%** | ## Summary - Rewrote `aiconfig-projects` skill description with concrete actions, third-person voice, and an explicit "Use when..." clause (description score: 33% → 100%) - Removed generic padding sections (Core Principles, What Are Projects?, Common Organization Patterns, What NOT to Do) that explained concepts the agent already knows - Added executable MCP tool call and REST API examples for project creation directly in the skill body - Added error recovery paths in the verification step (SDK init errors, 401/403, missing environments) - Collapsed the five-step workflow into a tighter four-step flow (Explore → Create → Implement → Verify) <details> <summary>Detailed changes</summary> **Description (frontmatter)** - Replaced vague description with specific actions: "Create and configure LaunchDarkly projects, extract SDK keys per environment, and verify SDK connectivity" - Added "Use when..." clause covering project creation, feature flag setup, SDK key extraction, and multi-team/region organization - Switched from second-person ("Helps you") to third-person voice **Content restructuring** - Removed ~110 lines of generic content: "What Are Projects?" explainer, "Core Principles" section, "Common Organization Patterns" examples, and "What NOT to Do" checklist - Merged Steps 1 and 2 into a single "Explore and Assess" step with inline scenario-routing table - Added concrete `create-project` MCP JSON payload and equivalent `curl` command in new Step 2 - Added explicit 409 Conflict handling guidance inline at the point of creation - Added three failure-recovery paths in verification: SDK key mismatch, permission errors, missing environments - Consolidated references section into a compact grouped format </details> I also stress-tested your `launchdarkly-flag-cleanup` skill against a few real-world task evals and it held up really well on safely removing launched flags while preserving production variation behavior. Kudos for that. Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags. ## Testing - [x] Manual (describe below) Ran `tessl skill review` before and after optimization. Score improved from 47% to 90%. All validation checks pass (valid frontmatter, name, description, compatibility, metadata). No changes to reference files or other skills. ## Notes - Only `aiconfig-projects/SKILL.md` is modified — no other skills touched - All 9 reference files in `references/` are unchanged and still correctly linked - The skill's existing cross-references from `aiconfig-create` and `aiconfig-migrate` remain valid Thanks in advance 🙏
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @nieblara 👋
this is genuinely impressive. The 24 skills cover the LaunchDarkly surface really thoroughly from flag lifecycle management to AI Config variations and guarded rollouts with metric monitoring. I especially love the meta angle of building skills for your own AI Configs product: feature flags for AI, taught to AI through skills. That’s clever, practical, and very on-brand.
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:Detailed changes
Description (frontmatter)
Content restructuring
create-projectMCP JSON payload and equivalentcurlcommand in new Step 2quick honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.
if you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.