v1.0.11

Doc consistency: the remaining '10 Threads formulas' references (post-writer, hook-extractor, repurposer) now read 13, and T11-T13 were added to the post-writer goal-pick and container selection tables. No behavior change.

v1.0.10

Doc fix: README now says 13 Threads hook formulas (T11 Status Flex, T12 Permission Reframe, T13 Copy-Swap added in v1.0.9). No behavior change.

v1.0.9

Corpus-validated the Threads hook formulas against 318 top English posts (Apify; text-native, so caption = hook). Raw-ranked (the search actor exposes no follower counts), so confidence was anchored on shapes that recur across unverified/small accounts.

• Added T11 First-Person Status Flex ("I'm a millionaire. Don't start a business.") — the top-of-feed shape, with no prior formula.
• Added T12 caps-forward Permission Reframe ("Most ADHD people DON'T NEED a stable career...") — top-3 from an unverified account; narrowed the T6 no-caps warning it contradicted.
• Added T13 Copy-Swap Micro-Lesson ("Instead of X, say Y") — the most repeatable small-account format.
• Noted the aspirational-warm skew vs X and the "let's connect" reply-farm lure as a non-signal. Propagated T11-T13 into post-writer + hook-extractor.

v1.0.8

v1.0.8 - Threads Audience Insights (read layer)

Adds an Apify-powered read layer, verified live against real Threads data.

New skill: threads-audience-insights (bundle now 8)

Read your Threads audience and niche from real numbers instead of guessing.

lib/apify_client.py - two live-verified methods

• fetch_niche_posts(query, sort) - top/recent Threads posts for a niche query or hashtag with likes, replies, reposts, and quotes (via igview-owner~threads-search-scraper).
• fetch_profile(username) - a profile's follower count, bio, verified status, and recent posts with engagement, yours or a competitor's (via apify~threads-profile-api-scraper).

Cached (256-entry LRU, 6h TTL), retries transient 429/5xx, works with a free Apify token or falls back to pasted posts.

Honest about the platform wall

Threads exposes no usable engager/liker roster (cookie-gated, ~100 cap, no public API). The read layer is discovery + profile stats + per-post counts only. It does not promise a liker list.

v1.0.7

Add the 7th skill: threads-profile-optimizer.

Audit and rewrite a Threads (Meta) profile end-to-end for 2026: profile photo, name with a searchable keyword, @handle, bio (150 chars, warm and specific), link, pinned post, and the connected-Instagram cross-pull that feeds Threads discovery. Returns a scorecard, priority fixes, and before/after rewrites.

Bumps the bundle from 6 to 7 skills and the package to 1.0.7.

v1.0.6

Add threads-repurposer skill: adapt content from LinkedIn, X, blogs, YouTube scripts, and newsletters into a native Threads post or thread. Warms the tone, de-corporates the source, refits to a short post or light thread, rebuilds the hook to clear the soft fold, strips off-platform artifacts, runs the humanizer, and publishes via Publora on approval. Bundle now ships 6 skills.

v1.0.5

Cross-runtime install docs: the README now documents OpenClaw and Hermes Agent install paths (Hermes reads SKILL.md per the agentskills.io standard and imports OpenClaw skills via hermes claw migrate), alongside the existing Codex, Claude Code, Claude Desktop, claude.ai, and skills-CLI options. Docs-only patch, no skill changes.

v1.0.4

Hardening patch (parity with linkedin-skills v1.0.10/v1.0.8 line).

• Security pack: SECURITY.md, HOL plugin-scanner CI workflow, dependabot config, requirements lockfile, .codexignore, and a branded plugin icon wired into the Codex manifest.
• Audit robustness verified: the pre-publish audit was pressure-tested (authority + deadline scenario, platform-adapted AI-tell drafts) and correctly FAILED the bad draft with full blocker lists. No rule gaps found.
• Writers: goal-first selection added where missing (YouTube community post writer, TikTok caption writer in their respective bundles).

No breaking changes. Patch release.

v1.0.3

Install option added: the README now includes the cross-agent skills CLI install path (npx skills add), which works in Claude Code, Codex, Cursor, and any agent that reads SKILL.md files, alongside the existing plugin-marketplace instructions. Patch release, no skill changes.

v1.0.2

Docs polish: every reference file longer than 100 lines now opens with a plain-text Contents list, so agents (and readers) doing a partial read see the full structure of the file before deciding which section to load. Insertions only, no content changes. Patch release.