prompt_improver
Skill2 starsChanged 3 months agoMITView on GitHub
Rewrite a rough prompt into a professional, structured prompt (role, context, task, instructions, constraints, output format, success criteria) using a LOCAL model — 0 cloud tokens — with markdown or strict JSON prompt output. Use when the user wants to improve/boost/structure a prompt, mentions "/p-amelioration", "prompt pro", "JSON prompt", prompt engineering, or wants a reusable prompt template built locally.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clean-cacheSkill
- agent-cacheSkill
- app_testSkill
- asset-qualitySkill
- auto_distillSkill
- auto-memorySkill
- auto_routerSkill
- benchSkill
- bootstrapSkill
- botte-proxySkill
- cacheSkill
- capabilitiesSkill
- cardinalSkill
- cavemanSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code_fingerprintSkill
- completion_proofSkill
- conductorSkill
- context_budgetSkill
- context_profilerSkill
- context_slicerSkill
- context_windowsSkill
- control_loopSkill
- cost_estimatorSkill
- cwe_kbSkill
- dag_optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff_languageSkill
- directives_auditSkill
- docgenSkill
- docs_stewardSkill
- eventsSkill
- fallow_likeSkill
- fast_contextSkill
- fixSkill
- harness_deltaSkill
- hermes-bridgeSkill
- hf_provenanceSkill
- infra_advisorSkill
- ingestSkill
- llm_backendsSkill
- llm_mcpSkill
- loaderSkill
- mcp_gatewaySkill
- meta_harnessSkill
- metricsSkill
- migration_auditSkill
- monte_cristoSkill
- mousquetairesSkill
- nlp_deterministicSkill
- nn_auditSkill
- prefix-prunerSkill
- prefix_treeSkill
- preflightSkill
- reportSkill
- The first 60 shown.
The file
Files
prompt_improver — pro structured prompts, built locally
Improving a prompt is text transformation, not hard reasoning — so it runs on a
local model for 0 cloud tokens (llm_backends). Output as structured markdown
or a strict JSON prompt object.
Run it (the /p-amelioration entry point)
python -m skills.prompt_improver.cli "make my code faster"
python -m skills.prompt_improver.cli "summarize this PR" --json
python -m skills.prompt_improver.cli "..." --no-local # deterministic scaffold onlyfrom skills.prompt_improver import improve
improve("rends mon code plus rapide", as_json=True)["json_prompt"] # cloud_tokens: 0The structure (well-established prompt-engineering practice)
| Field | Purpose |
role | who the model acts as |
context | only the background that matters |
task | one explicit objective |
instructions | ordered steps |
constraints | hard rules / what NOT to do |
output_format | exact shape of the answer |
examples | optional few-shot {input, output} pairs |
success_criteria | machine-checkable "done" conditions |
How it behaves
- With a local backend: the model rewrites the rough prompt into the schema (markdown or strict JSON, robustly parsed even through code fences).
- Without one (or
--no-local): returns a deterministic scaffold so the call never fails — then suggest installing a local model (see [[llm_backends]]).
Exposed via [[llm_mcp]] as the improve_prompt tool. Pairs well with
[[skill_finder]] (find tools for the improved task) and [[auto_router]] (run it
locally). Related global skills: prompt-engineering, prompt-builder, boost-prompt.
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.