Skip to content

feat: add /social-strategy skill — narrative architecture for founders (v0.12.12.0)#590

Open
ljagged wants to merge 17 commits intogarrytan:mainfrom
ljagged:feat-social-strategy
Open

feat: add /social-strategy skill — narrative architecture for founders (v0.12.12.0)#590
ljagged wants to merge 17 commits intogarrytan:mainfrom
ljagged:feat-social-strategy

Conversation

@ljagged
Copy link
Copy Markdown

@ljagged ljagged commented Mar 27, 2026

Summary

New /social-strategy skill helps founders build authentic public presence through strategic scaffolding, not content generation.

Three modes:

  • /social-strategy audit — autonomous social landscape research via WebSearch + browse. Maps competitor social activity, identifies 10-15 thought leaders with actionable engagement URLs, recommends platforms, generates voice prompt writing exercises.
  • /social-strategy — interactive 6-step strategy session: voice fingerprint (qualitative, not dimensional), content pillars, relationship priorities, platform plan, milestone alignment. Intermediate saves with DRAFT/COMPLETE status markers.
  • /social-strategy refresh — lightweight competitive re-scan. New immutable timestamped doc, never mutates existing artifacts.

Downstream integration:

  • /plan-ceo-review now discovers *-social-strategy-*.md and surfaces content pillars during scope decisions

ADRs:

  • 0003: Qualitative voice fingerprint over dimensional model
  • 0004: Narrative frameworks as panel of critics, not theories
  • 0005: Framework panel requires faithful representation (blocks framework-dependent features until human research)

Deferred to TODOS.md:

  • Framework panel curation (P1 prerequisite — requires human engagement with source material)
  • Review mode v1.1 (P1 — blocked on framework panel + voice fingerprint validation)
  • E2E eval tests (P2 — after dogfood)
  • Autoplan integration (P3)

Reviews

Review Status
CEO Review CLEAR (SELECTIVE EXPANSION, 3 expansions accepted)
Eng Review CLEAR (1 arch issue resolved, 0 critical gaps)
Outside Voice 2 Codex runs (19 findings total, 6 accepted as fixes)

Test Coverage

585 pass, 3 fail (all pre-existing on main). Gate-tier routing test added for /social-strategy. Periodic eval tests deferred to post-dogfood.

Pre-Landing Review

No issues found. All changes are prompt template, documentation, and test infrastructure.

Plan Completion

8/9 plan items DONE. VERSION + CHANGELOG handled by /ship.

Test plan

  • bun test — 585 pass, 3 pre-existing failures
  • bun run gen:skill-docs — social-strategy/SKILL.md generated (1026 lines)
  • bun run skill:check — no errors
  • Routing test added for social-strategy skill

🤖 Generated with Claude Code

divergentflow-old and others added 16 commits March 26, 2026 13:33
…hestration (v1.1.0)

Two modes: brief (autonomous competitive intelligence via WebSearch + browse)
and session (interactive Rumelt's kernel diagnosis with framework selection).
Produces versioned strategy documents with inline citations, milestone-gated
execution plans, and change tracking. Integrates with the gstack skill network.

v1.1 improvements from dogfood: broad market scan for competitor discovery,
browse-aggressive research, coherent actions with mutual support structure,
milestone-gated execution (not calendar months), brief amendment step, Codex
second opinion option, and "what did I miss?" validation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Both review skills now discover *-strategy-*.md files from /strategist
alongside design docs. Strategy docs provide competitive context and
guiding policy to inform scope and architecture decisions during reviews.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
CLAUDE.md: add /strategist to available skills list.
TODOS.md: add 3 items — CSO/retro artifact ingestion, autoplan
integration, and E2E eval test (all post-dogfood).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Standardize on gstack-slug everywhere (was mixing remote-slug and
  gstack-slug, causing Mode 1 write / Mode 2 read path mismatch)
- Add SLUG derivation to bash blocks that used it without re-deriving
- Fix description: "milestone-gated execution plans" not "90-day action plans"
- Add auto-chain retry guard: if Mode 1 fails, stop instead of retrying

Found by adversarial review (Claude subagent, 15 findings).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
feat: add /strategist skill — competitive strategy with framework orchestration (v0.11.22.0)
VERSION: upstream at 0.12.2.0, bumped to 0.12.3.0 for strategist feature.
CHANGELOG: strategist entry placed above upstream's 0.12.2.0 entry.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Resolved conflicts in VERSION, CHANGELOG.md, README.md.
Kept upstream version (0.12.11.0), upstream CHANGELOG entries,
and upstream's --single-branch --depth 1 clone command.
Preserved /strategist in skill lists from feat-strategist merge.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three Architecture Decision Records documenting:
- ADR 0003: Qualitative voice fingerprint over dimensional model
- ADR 0004: Narrative frameworks as panel of critics, not theories
- ADR 0005: Framework panel requires faithful representation
Three modes: audit (autonomous social landscape research via WebSearch + browse),
session (interactive 6-step strategy building: voice fingerprint, content pillars,
relationship priorities, platform plan, milestone alignment), and refresh
(lightweight competitive re-scan with immutable timestamped output).

Produces versioned voice, strategy, and style guide documents. Reads from
/strategist output. Never generates content to post.
CEO reviews now discover *-social-strategy-*.md artifacts and surface content
pillars and primary platform as informational context during scope decisions.
Gate-tier E2E routing test verifies Claude routes "social media strategy"
prompts to the social-strategy skill. Touchfile entry enables diff-based
test selection.
Skills list registration, README skill table entry, and 4 new TODOs:
framework panel curation (P1), review mode (P1), E2E eval (P2),
autoplan integration (P3).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@ljagged ljagged marked this pull request as draft March 27, 2026 22:56
Resolves conflicts in VERSION, CHANGELOG.md, CLAUDE.md, and README.md.
Upstream added /design-shotgun, /connect-chrome, design binary, pinned
dependencies, and community PR fixes (v0.13.1.0-v0.13.3.0).
Our branch adds /social-strategy skill and ADRs (0003-0005).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@ljagged ljagged marked this pull request as ready for review March 29, 2026 03:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants