developer-experience-review
Skill1 starsChanged 56 days agoMITView on GitHub
Audit a developer-facing surface: onboarding, docs, CLI; plan vs reality.
In this repository67 other files it gives its agents.
- architect-reviewerSkill
- backend-architectSkill
- backend-developerSkill
- code-architectSkill
- codebase-explorerSkill
- code-reviewerSkill
- code-simplifierSkill
- debuggerSkill
- error-detectiveSkill
- fullstack-developerSkill
- git-workflow-managerSkill
- legacy-modernizerSkill
- pragmatic-architectSkill
- prdSkill
- qa-expertSkill
- research-technical-spikeSkill
- sdd-spec-writerSkill
- security-auditorSkill
- supply-chain-securitySkill
- task-decomposition-expertSkill
- technical-debt-managerSkill
- test-engineerSkill
- typescript-proSkill
- architecture-decision-recordsSkill
- hermes-sdd-packagingSkill
- bug-diagnosisSkill
- build-craftSkill
- code-healthSkill
- code-review-checklistSkill
- commit-smartSkill
- context-architectureSkill
- design-explorationSkill
- design-to-htmlSkill
- diagram-tripletSkill
- dispatching-parallel-agentsSkill
- document-diataxisSkill
- e2e-testing-patternsSkill
- executing-plansSkill
- module-designSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- openspec-verify-changeSkill
- plan-scope-reviewSkill
- project-learningsSkill
- qa-test-plannerSkill
- requirements-claritySkill
- review-structuralSkill
- security-evidence-firstSkill
- agency-invocationSkill
- hermes-sdd-orchestrationSkill
- openspec-sddSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use when a developer-facing feature ships (API, CLI, SDK, library, onboarding, docs) or when asked to audit developer experience.
- Distinctive: line 22
Onboarding flow: do the docs get someone from zero to first success without dead ends?
- Distinctive: line 26
Error messages: when something breaks, does the error tell you what to do?
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- hermes-add-skill: concept adapted from gstack /devex-review (garrytan/gstack, MIT) —
the "boomerang": measure the plan promise against real developer experience. -->Developer experience review
Actually test the developer experience of a developer-facing surface (onboarding, docs, CLI, API, SDK) and report where the plan promised diverges from how it actually is. The value is in the gap — the boomerang between the doc's "getting started in 3 minutes" and the reality of 8.
Use when a developer-facing feature ships (API, CLI, SDK, library, onboarding, docs) or when asked to audit developer experience.
What to measure
- Time to hello-world (TTHW): from a cold start to the first working example, timed for real, not estimated.
- Onboarding flow: do the docs get someone from zero to first success without dead ends?
- Doc quality by task: can a developer do the thing (a how-to), not just read concepts?
- CLI/help text: is the surface discoverable and does the help text resolve the next step?
- Error messages: when something breaks, does the error tell you what to do?
Plan vs reality (the boomerang)
- Compare measured reality against what the plan or docs promised.
- A promised time/score that reality misses is a defect with
path:line+ the measured number, not a mood. - Produce a DX scorecard with evidence (timing, screenshots, exact error text), and a before/after when a fixing pass runs.
Rules
- Measure the real surface — don't re-read the design doc and declare DX good.
- A claim "onboarding is smooth" needs the timed run plus the friction points found.
- Fixing the DX is its own change; the review reports the scorecard, the fix goes back to
the builder with evidence (per
rules/quality.md).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.