v3.3.0

[3.3.0] - 2026-04-18

Added

• beagle-analysis: Add web-research skill — reusable research primitive that turns a sharp research question into a written plan, parallel-subagent findings, and a cited synthesis report (TL;DR / Findings / Gaps & Limitations / Sources) on disk. Dual-mode: directly invocable by users and programmatically invocable by companion skills (prfaq-beagle, brainstorm-beagle, strategy-interview) via a documented contract (#96)
• beagle-analysis: Add artifact-analysis skill — sibling primitive to web-research that scans local documents and project knowledge (auto-discovering .beagle/concepts/, .planning/, docs/, and root README/brief files by default) via parallel subagents and produces a path-cited synthesis report with fixed sections (Documents Found / Key Insights / User / Market Context / Technical Context / Ideas & Decisions / Raw Detail Worth Preserving / Gaps & Limitations). Dual-mode with the same companion contract used by prfaq-beagle, brainstorm-beagle, and strategy-interview (#96)
• beagle-analysis: Add prfaq-beagle skill — hardcore Working Backwards PRFAQ coach that runs a 5-stage gauntlet (Ignition → Press Release → Customer FAQ → Internal FAQ → Verdict) to filter weak product, internal-tool, or OSS concepts before they consume brainstorm-beagle cycles. Detects concept type in Ignition and calibrates later stages; invokes web-research and artifact-analysis serially for grounding with graceful degradation on web-tools-unavailable and resume-by-default on prior-run-present. Binary pass/fail verdict — on pass, produces a concept brief at .beagle/concepts/<slug>/brief.md that brainstorm-beagle auto-ingests; on fail, produces targeted feedback naming exactly what stage to re-enter and what would need to be true (#96)

Changed

• beagle-analysis: Update brainstorm-beagle — relocate spec output from docs/specs/YYYY-MM-DD-<topic>.md to .beagle/concepts/<slug>/spec.md; auto-detect brief.md at startup and ingest it to skip most discovery; when invoking web-research or artifact-analysis mid-session, land their outputs under the shared .beagle/concepts/<slug>/research/ and .beagle/concepts/<slug>/analysis/ folders so the whole concept-forging audit trail lives in one place (#96)

v3.2.0

[3.2.0] - 2026-04-18

Added

• beagle-analysis: Add resolve-beagle skill — follow-up to brainstorm-beagle that orchestrates parallel research subagents (with sequential inline fallback) to close Open Questions and latent gaps in a spec, presents proposals one at a time for approval, and rewrites the spec in place (#94)

Fixed

• beagle-core: Make gen-release-notes Step 5 explicit about updating [Unreleased] and inserting the new [VERSION] footer compare links, with an example diff and a verification grep — prevents the recurring CodeRabbit feedback that release PRs were missing footer reference links (#95)
• release command: Add Step 3.5 verification gate that fails the release flow if CHANGELOG footer compare links for the new version are missing (#95)

Full Changelog: v3.1.0...v3.2.0

v3.1.0

[3.1.0] - 2026-04-11

Added

• beagle-rust: Add macros-code-review skill for macro_rules!, proc macros, hygiene, fragment specifiers, and span handling (#92)
• beagle-rust: Add ffi-code-review skill for extern "C", repr(C), CStr/CString, callbacks, and bindgen patterns (#92)
• beagle-rust: Add 10 new reference files across existing skills: lifetime-variance, types-layout, unsafe-deep, concurrency-primitives, api-design, ecosystem-patterns, advanced-testing, features-conditional, no-std, pinning-cancellation (#92)

Changed

• beagle-rust: Update all skills for Rust 2024 edition — RPIT lifetime capture, unsafe_op_in_unsafe_fn, async fn in traits, LazyCell/LazyLock, resolver v3 (#92)
• beagle-rust: Update review-rust orchestrator to detect and route macros/FFI to new skills (#92)
• beagle-rust: Expand verification protocol with macro, FFI, and concurrency false positive rules (#92)

v3.0.0

[3.0.0] - 2026-04-11

Removed

• beagle-analysis: Remove deprecated 12-factor-apps and 12-factor-apps-analysis skills, superseded by agent-architecture-analysis (#90)

Changed

• BREAKING: Rename brainstorm skill to brainstorm-beagle to resolve ClawHub slug conflict (#90)
• BREAKING: Rename humanize skill to humanize-beagle to resolve ClawHub slug conflict (#90)
• beagle-analysis: Optimize skill descriptions for improved triggering accuracy (#90)

Fixed

• beagle-analysis: Remove stale reference to deleted 12-factor-apps skill in agent-architecture-analysis description (#90)

v2.12.1

[2.12.1] - 2026-04-10

Changed

• beagle-analysis: Improve strategy skill discoverability with expanded marketplace tags and refined trigger phrases (#88)

v2.12.0

[2.12.0] - 2026-04-10

Added

• beagle-analysis: Add strategy-interview skill for structured strategy interviews using kernel framework with landscape mapping, choice cascade, and value innovation lenses (#85)
• beagle-analysis: Add strategy-review skill to pressure-test strategy documents for kernel integrity, bad-strategy patterns, coherence gaps, and untested assumptions (#85)

Changed

• beagle-docs: Refactor humanize skill to use references/ directory for vocabulary swaps, fix strategies, and developer voice guidelines (#85)
• beagle-docs: Add 10 new humanize fix categories: em dash overuse, thematic breaks, title case headings, curly quotes, negative parallelism, challenges-and-prospects formula, rule of three, inline-header lists, unnecessary tables, regression to mean (#85)
• Remove deprecated beagle plugin entry from marketplace manifest (#85)

v2.11.0

[2.11.0] - 2026-04-04

Added

• beagle-rust: Add rust-best-practices skill for idiomatic Rust patterns, ownership guidelines, and error handling conventions (#83)
• beagle-rust: Add rust-project-setup skill for project scaffolding, Cargo workspace configuration, and toolchain setup (#83)

v2.10.0

[2.10.0] - 2026-04-03

Added

• beagle-testing: Enforce E2E-only test plans — prohibit wrapping automated test suites (cargo test, pytest, npm test) and require real user-facing actions (#79)
• beagle-testing: Add Rust and Elixir stack detection, CLI/database test templates, and structured setup format (#79)

Changed

• beagle-testing: run-test-plan updated to handle both new and legacy setup formats (#79)

v2.8.0

[2.8.0] - 2026-03-27

Added

• beagle-analysis: Brainstorm skill for idea-to-spec workflow with structured spec generation and review (#74)

Fixed

• beagle-core: Fix suggestion-block stripping order in fetch-pr-feedback — suggestion markers are now removed before blanket HTML comment removal (#74)

v2.7.1

[2.7.1] - 2026-03-21

Fixed

• beagle-core: Preserve substantive details blocks in fetch-pr-feedback command (#72)

Changed

• Update beagle-ios skill count in README (12 → 15) (#71)