Skip to content

stevesolun/ctx / docs

skill-router

Flagged

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

FileKindSize
SKILL.mdskill md9.3 KB
assets/javascripts/catalog.jsscript2.5 KB
assets/javascripts/repo-stats-refresh.jsscript3.2 KB
backup-hook-install.mdmarkdown9.2 KB
catalog.mdmarkdown10.3 KB
ctx-fit/ARCHITECTURE_CANDIDATES.mdmarkdown12.9 KB
ctx-fit/ARCHITECTURE_GAP_ANALYSIS.mdmarkdown10.7 KB
ctx-fit/CTX_AUDIT.mdmarkdown11.6 KB
ctx-fit/CURRENT_STATE.mdmarkdown16.3 KB
ctx-fit/DECISIONS.mdmarkdown15.7 KB
ctx-fit/GOOD_FIRST_ISSUES.mdmarkdown20.6 KB
ctx-fit/IMPLEMENTATION_TRACKER.mdmarkdown697 B
ctx-fit/MAP.mdmarkdown7.8 KB
ctx-fit/PRD.mdmarkdown9.7 KB
ctx-fit/STATE.mdmarkdown60.9 KB
ctx-fit/milestones/M1_SPIKE_FRICTION_LOG.mdmarkdown5.5 KB
ctx-fit/milestones/MILESTONE_00_AUDIT.mdmarkdown5.1 KB
ctx-fit/planned_tasks.mdmarkdown17.7 KB
dashboard.mdmarkdown24.7 KB
enterprise-readiness-review.mdmarkdown8.7 KB
entity-onboarding.mdmarkdown18.0 KB
harness/attaching-to-hosts.mdmarkdown16.2 KB
harness/clean-host-contract.mdmarkdown4.5 KB
harness/loopflow-adapter-demo.mdmarkdown11.1 KB
huggingface-publish.mdmarkdown3.3 KB
index.mdmarkdown22.4 KB
knowledge-graph.mdmarkdown22.7 KB
marketplace-registry.mdmarkdown4.0 KB
memory-anchor.mdmarkdown2.7 KB
plans/ctx-agent-reviewer-workbench.mdmarkdown12.4 KB
plans/unified-capability-engine.mdmarkdown59.0 KB
qa/dashboard-user-story-status.csvother26.0 KB
qa/feature-user-story-status.csvother92.5 KB
research/context-engineering-guidance-audit.mdmarkdown10.4 KB
services/macos/com.claude.backup.watchdog.plistother1.7 KB
services/systemd/claude-backup-watchdog.serviceother1.3 KB
skill-lifecycle-and-dashboard.mdmarkdown6.2 KB
skill-quality-install.mdmarkdown6.2 KB
skill-router/index.mdmarkdown2.5 KB
skill-stack-matrix.mdmarkdown5.5 KB
skills-health.mdmarkdown3.5 KB
stack-signatures.mdmarkdown6.2 KB
telemetry.mdmarkdown24.7 KB
threat-model.mdmarkdown15.0 KB
toolbox/behavior-miner.mdmarkdown2.6 KB
toolbox/configuration.mdmarkdown4.0 KB
toolbox/council-runner.mdmarkdown2.4 KB
toolbox/hooks.mdmarkdown2.6 KB
toolbox/index.mdmarkdown3.0 KB
toolbox/intent-interview.mdmarkdown3.0 KB
toolbox/starters.mdmarkdown3.0 KB
toolbox/templates/docs-review.jsonconfig599 B
toolbox/templates/fresh-repo-init.jsonconfig533 B
toolbox/templates/refactor-safety.jsonconfig634 B
toolbox/templates/security-sweep.jsonconfig636 B
toolbox/templates/ship-it.jsonconfig676 B
toolbox/verdicts.mdmarkdown4.0 KB

huggingface-publish.md

View on GitHub
# Hugging Face Publish

ctx publishes the GitHub repository as the public Hugging Face dataset repo
[`Stevesolun/ctx`](https://huggingface.co/datasets/Stevesolun/ctx). The
dataset repo is a clean `git ls-files` snapshot plus the two exact archives
declared by `graph/release-artifacts.json`, not local review reports or ignored
caches.

## What gets uploaded

- Tracked source, docs, tests, and packaging files.
- `graph/wiki-graph.tar.gz`.
- `graph/wiki-graph-runtime.tar.gz`.
- The compressed skill index under `graph/`.
- Tracked graph visualizations under `graph/`.

Ignored local reports, review notes, raw ingest caches, coverage files,
`site/`, and `.pytest_cache/` are not uploaded because they are not tracked
by git.

## Automatic publish

Every push to `main` runs `.github/workflows/huggingface-sync.yml`. The job
checks out source, strictly validates `graph/release-artifacts.json`, and
hydrates only its two large archives from the named GitHub release. It verifies
all five graph assets by exact size and SHA-256, with no Git LFS fallback. It
then installs the sync dependencies and calls
`scripts/sync_huggingface.py`. It publishes only when the repository secret
`HF_TOKEN` is configured. On the canonical
`stevesolun/ctx` repository, a missing token is a hard failure so main cannot
silently drift from the dataset repo. On forks, a missing token still exits
successfully with a notice because forks are not trusted publishing sources.

When only repo-card inputs changed (`README.md`, `CHANGELOG.md`, or files under
`docs/`), the workflow uses card-only upload mode. Source, test, workflow, graph,
or packaging changes always run the full dataset sync so tracked files cannot
drift behind GitHub.

The sync script is still the contract: it exports the tracked git snapshot,
adds the two manifest-declared archives, adds Hugging Face repo-card metadata,
validates README/docs stats, and refuses missing, stale, or corrupt artifacts.

## Manual publish

Use the repository sync script. It exports tracked files plus the validated
local graph artifacts, adds the Hugging Face repo-card frontmatter to the
uploaded `README.md`, and refuses to publish if the manifest or any full wiki,
runtime wiki, or compressed skill-index byte identity is missing or mismatched.

Full sync uploads the exported tree with `delete_patterns="*"`, so files removed
from the current git snapshot are removed remotely in the same commit.
Card-only sync exports only `README.md`, `CHANGELOG.md`, and tracked `docs/**`
inputs, then replaces just those remote paths.

Do not paste the token into a command line. Prompt for it, set it only for the
current process, and clear it after the upload.

```bash
python -m pip install --upgrade huggingface_hub

read -rsp "HF write token: " HF_TOKEN
printf '\n'
export HF_TOKEN
trap 'unset HF_TOKEN' EXIT
python scripts/sync_huggingface.py --repo . --repo-id Stevesolun/ctx --repo-type dataset
unset HF_TOKEN
trap - EXIT
```

For a README/changelog/docs-only refresh:

```bash
python scripts/sync_huggingface.py --repo . --repo-id Stevesolun/ctx --repo-type dataset --card-only
```

## Verify

```bash
python - <<'PY'
from huggingface_hub import HfApi

api = HfApi()
info = api.repo_info(repo_id="Stevesolun/ctx", repo_type="dataset")
print(info.id, info.sha)
PY
```

The dataset page should show the MIT license and the tags from the metadata
wrapper.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall