Changelog
23 entries across 17 skills, newest first, from each skill's CHANGELOG.md.
Every push that bumps a version is also published as a
GitHub release.
November 2026
-
writing-reportsv2.0.0
Changed
- Reports are now written as short research papers: structured Abstract (Background, Objective, Methods, Results, Conclusions), then numbered Introduction, Methods, Results, Discussion, Limitations and Conclusion sections. The Verdict / Findings / Caveats layout is retired.
- Every number carries an evidence type (measured, third-party benchmark, vendor-reported, community report, derived), and claims are hedged to match.
- Report types (benchmark study, evidence review, technical investigation, technical guide) adjust the Methods and Results sections.
- Search goes through Camofox instead of SearXNG.
Added
- Rules for rewriting an older report into the new format without changing its facts.
-
impeccablev4.9.0
Changed
- Synced to upstream Impeccable 4.9.0 (engine 0.1.23) via
npx impeccable install -y --providers=hermes --globalinto a scratch HOME, then copied in; files remain byte-identical to that install.
- Synced to upstream Impeccable 4.9.0 (engine 0.1.23) via
-
writing-reportsv1.1.0
Changed
- References are numbered in order of first citation (
[n] Title: <URL>), and every sourced claim carries an inline[n]marker. The docs site renders these as linked superscripts with a hover preview and back-links. - The template drops the
---separators between sections.
- References are numbered in order of first citation (
-
slack-mention-watchv2.7.1
Fixed
- A queued review update is dropped when
SLACK_REVIEW_AGENTchanged since it was queued (review: dropped queued update for <id> (...: agent is now <agent>)), instead of being sent to the old agent's session. - Queued targets that no longer need a review (merged, approved, ...) are no longer pulled into a follow-up run. A failed resume is not retried in the same tick; its update stays queued.
- Each target's PR/ticket status is checked once per tick, not once per use.
- A started review run is saved to
SLACK_REVIEW_STATEright away, so a later error in the same tick no longer loses it and the target is not reviewed twice. - PR review asks match whole words only: "looks", "checked" or "testing" alone no longer count as a review request.
- The read-only guard also allows
gh run/gh workflowview/list,gh search,gh status,gh issue status,git branchlisting flags andgit remote -v/show/get-url.
- A queued review update is dropped when
-
slack-mention-watchv2.7.0
Fixed
- Review agent: only explicit review asks in the
Mention:text start a review (PTAL, "can you review", "please check this", ...), not any PR link or ticket key in the block. Targets come from the mention, else the thread root only. Other pings getreview: skipped (not a review request); asks without a targetreview: skipped (no target in mention or thread root). - Review dedupe is per target: one new target no longer re-reviews the others, and nothing is reviewed again just because 24 h passed (PRs: until the head commit changes; tickets:
SLACK_REVIEW_DAYS, 7). - Review runs are read-only for every agent: git/gh guard wrappers first on the agent's PATH run only an allowlist of read-only git/gh commands (gh api: GET only) and block the rest, aliases included; claude no longer allows
gh api(it allowed POSTs, e.g. PR comments). Argv checks, not a sandbox (see "Write guarantee").SLACK_REVIEW_GUARD=0turns them off.
Added
- Follow-ups resume the target's existing omp/claude session (
review: resumed <id> (..., old..new)) with a brief holding the new Slack block(s) and, for PRs, only theold..newdiff. A session still running gets the update queued (review: busy <id> (update queued)), delivered on a later tick. review_spawn.py --sessionsprints the session table (read only).- Opt-in Jev second opinion for review asks (
SLACK_REVIEW_JEV=1+TYPESAFE_API_KEY,SLACK_REVIEW_JEV_MIN0.8, log inSLACK_REVIEW_JEV_LOG); the Jev shadow log asks the samereviewquestion.
Changed
SLACK_REVIEW_STATEholds a session table per target (session, agent, runs, reviewed head commit, pid, queued updates); entries are pruned after 30 days without a run. Pre-2.7 files are migrated on the next save; migrated entries are never resumed. Thereview: already runningline is gone.
- Review agent: only explicit review asks in the
-
auditing-worktreesv1.0.0
- Initial tracked version.
-
camofox-browserv1.0.0
- Initial tracked version.
-
covidence-full-text-retrievalv1.2.0
- Initial tracked version.
-
covidence-full-text-reviewv2.0.0
- Initial tracked version.
-
covidence-screeningv1.0.0
- Initial tracked version.
-
demo-runbookv0.1.0
- Initial tracked version.
-
hermes-deepseek-cachev1.1.0
- Initial tracked version.
-
ilearning-autoadvancev5.0.0
- Initial tracked version.
-
impeccablev4.8.0
- Initial tracked version.
-
multi-repo-pr-review-merge-roundv1.0.0
- Initial tracked version.
-
oh-my-ghosttyv1.0.0
- Initial tracked version.
-
sci-hub-accessv1.1.0
- Initial tracked version.
-
slack-mention-watchv2.6.0
Added
- Opt-in Jev shadow mode (
SLACK_MENTION_JEV_SHADOW=1+TYPESAFE_API_KEY): logs TypeSafe Jev's emoji verdict and already-handled probability for each new mention to~/.hermes/scripts/.slack-mention-jev.jsonlbeside the regex result. Sends mention and thread text toapi.typesafe.ai; off by default; changes no output or reaction.
Changed
- Digest cron example uses
--reasoning-effort high, notmax(maxwas ~88% of the job's spend).
- Opt-in Jev shadow mode (
-
slack-mention-watchv2.5.0
- Initial tracked version.
-
slack-scanv1.0.0
- Initial tracked version.
-
superpowers-using-superpowersv1.0.0
- Initial tracked version.
-
tldrv1.1.0
- Initial tracked version.
-
writing-reportsv1.0.0
- Initial tracked version.