Automated summary
This slash command turns a mistake, review, or failed test into a skill improvement proposal, following the repository's APEX protocol.
Strengths
- Runs a complete, deterministic workflow: context compilation, schema validation, template-based authoring, registry and traceability updates
- Ships explicit success criteria, a failure-mode table with remediations, and a documented rollback procedure
- Relies on existing automated gates (structure check, sync_registries, drift checkers) instead of manual verification
Limitations
- Tightly coupled to the APEX directory layout (13_skills, 18_registry, 25_automation) and unusable as-is outside that repo
- Assumes preconditions are already green (structure CI, synced registries) and that the caller has write access to the proposals folder
- Invocation is presented as pseudocode; real execution depends on the agent harness
Use it when a failed test, a review finding, or a known mistake should become a traceable, schema-validated skill improvement proposal inside the APEX repository.
Avoid it for authoring a standalone skill or working outside the APEX repo, since the referenced paths, schemas, and sync scripts would not exist.
Security analysis
SafeThe skill is a workflow specification for generating improvement-proposal artifacts inside an internal repo. It does not fetch or pipe remote content, does not touch secrets/tokens, and its only shell actions are benign registry-sync and git revert commands. No obfuscation or safety-disabling behavior is present.
- •References execution of repo-local Python scripts (sync_registries.py, compile_context.py) and git revert, but all operations are non-destructive and confined to the repository workflow
- •Path references use relative traversals (../../..) that assume a specific repo layout; no data leaves the repo
Examples
/apex:improve_skill target=ATLAS — the slicing test failed because the skill didn't validate the slice id format; create an improvement proposal./apex:improve_skill target=ATLAS — code review flagged that the context compiler is called before input validation; turn this into a skill improvement proposal with evidence.Slash Command: /apex:improve_skill
Purpose
Create a skill improvement proposal from a mistake, review, or failed test.
Output
13_skills/skill_refinery/improvement_proposals/
Inputs
target(string, required): the entity being acted on (repo name, slice id, etc.)- Source-of-truth files: see 19_truth_state/source_of_truth_ranking.yaml
- Relevant schemas: 26_schemas/
Preconditions
- Repo structure check passes (apex_structure_check.yml)
python3 25_automation/registry_sync/sync_registries.py --checkis green- Caller has write access to
13_skills/skill_refinery/improvement_proposals/
Step-by-step
1. Load context
Compile a context packet via 42_context_compiler/compile_context.py for the appropriate persona (12_agents/personas/).
2. Validate inputs
- Required input fields present.
- Input matches the relevant schema in 26_schemas/.
- No conflicts with existing artifacts in
13_skills/skill_refinery/improvement_proposals/.
3. Author artifact
- Use the matching template in 14_templates/.
- Reference the active ADRs (04_architecture/adrs/) and skills (13_skills/active/).
- Write artifact to
13_skills/skill_refinery/improvement_proposals/with a deterministic filename.
4. Update registries
- Run
python3 25_automation/registry_sync/sync_registries.py --writeto refresh the relevant*.registry.yaml. - Add a row to 18_registry/change_ledger.yaml.
5. Update traceability
- If artifact is a spec/ADR/diagram/test/evidence/release, add a row to 18_registry/traceability.yaml.
6. Validate
- Schema-validate the new artifact.
- Run drift checkers under 25_automation/drift_checkers/.
7. Capture evidence
- Append an evidence packet to 23_evidence/evidence_packets/ referencing the new artifact.
Outputs
- Artifact in
13_skills/skill_refinery/improvement_proposals/ - Updated
*.registry.yaml - Change ledger row
- Optional evidence packet
- Optional drift report
Success criteria
- New artifact exists, validates against schema, is referenced from the appropriate registry, and CI continues to pass.
Failure modes
| Failure | Detection | Remediation |
|---|---|---|
| Schema mismatch | schema-validate CI gate | fix artifact to match schema |
| Registry drift | registry-sync-check | sync_registries.py --write |
| Missing prerequisite | structure-check fails | seed required directory/file |
| Duplicate artifact id | author-time check | choose next free ID |
| OneDrive sync collision | hash mismatch on rerun | re-run after sync settles |
Rollback
Revert the commit that introduced the artifact:
git revert <sha>
python3 25_automation/registry_sync/sync_registries.py --write
Example invocation
# Pseudocode — actual invocation is via the agent harness
/apex:improve_skill target=ATLAS
See also
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/apex-improve-skill-improvement-proposal-mrwake34/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/apex-improve-skill-improvement-proposal-mrwake34' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/apex-improve-skill-improvement-proposal-mrwake34/download' --output '.skill-downloads/apex-improve-skill-improvement-proposal-mrwake34/SKILL.md.part' && mv '.skill-downloads/apex-improve-skill-improvement-proposal-mrwake34/SKILL.md.part' '.skill-downloads/apex-improve-skill-improvement-proposal-mrwake34/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/apex-improve-skill-improvement-proposal-mrwake34/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.