mikeparcewski/wicked-garden / skills/learn
wicked-garden-learn
VerifiedLearn from outside sources, every claim cited. Learn mode: research a topic or event, synthesize a claims ledger (each claim with its source URL and observed_at), walk the operator through it, then author .wicked/knowledge/<slug>/ plus text-only skills that cite the claims; a refresh proposes only changes (confirm, supersede, contradict, retire), never a silent delete. Report mode (the `sourced-report` workflow): the same research and synthesis, without the write-up, from staged documents, the job's picked sources and the web, then a fidelity check by a seat that did not gather. It changes nothing. Use when: "learn about X", "research X and save what we learn", "what happened with <event>", "refresh the knowledge on X", "check the learned knowledge", a brief with a `Lens:` line, or a phase of the `learn` or `sourced-report` workflow. NOT for this repository's own code (wicked-garden-repo-learn) or for what the operator told you (a memory: wicked-garden-mem).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.7 KB |
| refs/claims.md | markdown | 2.7 KB |
| refs/refresh.md | markdown | 2.8 KB |
| refs/report-analyze.md | markdown | 1.2 KB |
| refs/report-check.md | markdown | 4.4 KB |
| refs/report-claims.md | markdown | 7.1 KB |
| refs/report-competitive.md | markdown | 1.2 KB |
| refs/report-critique.md | markdown | 1.3 KB |
| refs/report-due-diligence.md | markdown | 1.3 KB |
| refs/report-estimate.md | markdown | 1.4 KB |
| refs/report-research.md | markdown | 1.1 KB |
refs/refresh.md
View on GitHub# Refresh: re-research, propose only changes
A refresh is a `learn` run on a topic that already exists. The scope step names it, because
`.wicked/knowledge/<slug>/` is already in the tree. A scheduled refresh is launched by wicked-crew's
learn schedule, and its intent says so. A refresh changes only what the evidence changes.
## Synthesize: the diff
Classify every **active** claim, and then every new candidate, into exactly one bucket:
| Bucket | When | What the author does |
|---|---|---|
| confirmed | A fresh fetch of a source still supports the claim. | Set `last_verified` to now. The text and id stay the same. |
| superseded | A newer source states it differently, for example a new version or a changed default. | Add the new claim, with its own id and sources. On the old claim, set `status: superseded`, `superseded_by`, `reason` and `evidence`. |
| contradicted | A credible source says the claim is wrong. | Set `status: contradicted`, with `reason` and `evidence`. If a corrected claim exists, add it. |
| retired | The claim no longer applies: the feature was removed, or the event is over and no longer matters. Also use this when the claim is **unverifiable**: no source supports it now, and its `last_verified` is more than two refresh intervals old. | Set `status: retired`, with `reason` (`unverifiable` is a valid reason). For `evidence`, cite the fetch that failed or the page that shows the change. |
| new | A candidate that matches no existing claim. | Add it. |
Put the diff in your output as a table with one row per claim id, then counts per bucket. The
walkthrough teaches the diff first: "what changed since <refreshed_at>".
## Author: the pull request is the proposal
- Never delete a line from `claims.jsonl`. A removal is a status change with its reason and evidence.
- Remove each non-active claim from README.md and from every skill that cites it. Rewrite the
sentence around the replacing claim, if there is one.
- Set `refreshed_at` on topic.json and add this run's id to `run_ids`.
- A refresh with no material change still bumps `last_verified` on each claim it re-saw. That makes
the pull request a small "verified, nothing changed" record. The operator may decline it at the
deliver gate.
## Review: the evaluator checks the removals
- Re-fetch the evidence for every status change.
- A retirement that is not supported by evidence is a FAIL.
- So is a contradiction with no credible source, or a claim silently dropped from the ledger.
## Afterwards
- **Merging is the approval.** Once the pull request is merged, `wicked-garden run scripts/learn/index.py --repo <checkout>`,
run by the operator or by the crew schedule tick, replaces the topic's estate scope.
- **Recall follows the merged ledger.** A claim that is no longer active leaves knowledge recall.
- **History stays in the repository.**
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |