mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-08-28 04:24:58 +00:00

fix(stream): post-merge required changes for PRs #895/#926/#942/#943/#944/#965 + counter true-up + #964 guard + #954 doc drift

Applies every pre-merge required change from audit/pr-stream-2026-08/ that
could not land on contributor forks, plus the stream's cross-cutting fixes:

- stock-analysis (#944): description trimmed 1463 -> 1001 chars; Anti-Patterns
  + Cross-References sections added; security-auditor false positive at
  holdco-assetmgr.md:58 suppressed inline (auditor:ignore-line) -> strict PASS
- deepread (#965): renamed research/dsh-deepread -> research/deepread; H1 and
  name updated; research-summarizer cross-ref path-qualified; 12 cited sources
  added across both references; plugin.json + marketplace entry; routed in the
  research orchestrator (SKILL.md registry + SIGNALS + classifier.py in
  lockstep, verified: 'deeply read this pdf' -> deepread, 3 signals)
- business-name-fit (#926): 'Use whenever' -> 'Use when' (validator trigger
  regex); +2 cited sources (USPTO TMEP §1209, Usunier & Shaner 2002) -> 5
- embedded-iot-mentor (#942): references/hardware-selection.md (7 sources,
  datasheet-anchored) + worked mini-example; validator length gate now passes
- swedish-mentor (#943): references/swedish-resources.md (6 sources, stable
  official URLs only); session recipes, milestones, learner situations,
  worked example; mandated opener softened to guidance; plugin.json +
  marketplace entry; validator length gate now passes
- Related Projects (#895): LinkedIn Skills row trued up (10 -> 11 skills,
  hardcoded star count dropped)
- check_plugin_json.py: marketplace description <= 1024 guard added to --all
  (the #964 regression guard; commercial-skills sits at 1021/1024)
- #954 doc drift: quality_gates_for_skills.md, cs-skill-author.md,
  security-guidance SKILL.md now point attribution at authoring-notes.json
- Counter true-up after the 6-skill merge batch: 370 skills / 672 tools /
  809 refs / 92 plugins across README.md badge+table, CLAUDE.md, marketplace
  metadata (derive_counters.py --check passes)

All gates green locally: frontmatter 0 errors, model freshness 0 findings,
dual-publish 0 drifted, paths 0, smoke 0 failed, plugin-json 0 FAIL.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Bzm6Pafyxja6g4jUDPcei

2026-08-21 09:01:24 +00:00

3 KiB

Raw Permalink Blame History

Evidence-Centered Knowledge Map

Use this reference for map mode. A useful map preserves reasoning, not just headings.

Node Types

THESIS: the central claim or explanatory model.
CLAIM: a supporting or opposing proposition.
REASON: a logical bridge between claims.
EVIDENCE: an observation, quotation, record, or study.
DATA: numerical evidence with unit, population, period, and baseline.
EXAMPLE: an illustration that does not by itself establish generality.
CONCEPT: a term whose definition matters to the argument.
ASSUMPTION: an unstated premise.
COUNTERARGUMENT: an alternative conclusion or explanation.
LIMITATION: a boundary on scope or confidence.
QUESTION: an unresolved issue or retrieval prompt.

Edge Labels

Every edge must use a meaningful label: supports, explains, defines, illustrates, depends on, qualifies, contradicts, or raises.

Never use unlabeled proximity as a substitute for a relationship.

Required Metadata

For evidence and data nodes, include:

source location;
the claim they connect to;
confidence label;
missing context or caveat.

Markdown Output

THESIS: [central claim]
├── supports → CLAIM: [supporting claim]
│   ├── because → REASON: [logical bridge]
│   ├── supports → EVIDENCE: [evidence] ([location])
│   └── qualifies → LIMITATION: [boundary]
├── depends on → ASSUMPTION: [unstated premise]
└── contradicted by → COUNTERARGUMENT: [strong alternative]

When the user requests FreeMind or XMind-compatible output, render the same hierarchy as valid FreeMind XML and escape all source-derived text used in XML attributes.

Quality Check

Before delivering the map, verify:

Every major claim connects to the thesis.
Every evidence node connects to a specific claim.
Examples are labeled as examples.
Contradictions and limitations remain visible.
The map contains no conclusion that exists only because of layout.

Sources

Novak, J. D. & Cañas, A. J. — "The Theory Underlying Concept Maps and How to Construct and Use Them" (IHMC CmapTools Technical Report, 2008) — the concept-mapping method this map structure derives from.
Toulmin, S. — The Uses of Argument (1958) — claim / grounds / warrant decomposition mirrored by the claim–reason–evidence fields.
Ahrens, S. — How to Take Smart Notes (2017) — atomic, linked notes as durable knowledge structure.
Adler, M. J. & Van Doren, C. — How to Read a Book (1972) — syntopical reading: mapping how multiple sources answer the same question.
Weinstein, Y., Madan, C. R. & Sumeracki, M. A. — "Teaching the Science of Learning", Cognitive Research 3 (2018) — elaboration and concrete-example strategies encoded in the map's link labels.
Hattie, J. & Donoghue, G. M. — "Learning Strategies: A Synthesis and Conceptual Model", npj Science of Learning 1 (2016) — where organization/mapping strategies help in the acquisition→consolidation cycle.

3 KiB Raw Permalink Blame History Unescape Escape