Eleven skills for recovering context, making diagrams, working safely while you're
away, and closing the gap between what you planned and what actually happens —
one for plain-language answers, one for recall, one for visualising, one for working a queue, two for autonomous
runs, one before you start, one for mid-build, three for when you think you're done.
Built after reading Thariq's field guide to Fable.
install all eleven
for s in 1by1 blind-spot-pass deviation-log spot-check merge-quiz pitch-me; do
mkdir -p ~/.claude/skills/$s
curl -fLsS https://mrcoder.github.io/skills/$s/SKILL.md -o ~/.claude/skills/$s/SKILL.md
done
# no-bs is one skill; renhua is its backwards-compatible alias.
for s in no-bs renhua; do
mkdir -p ~/.claude/skills/$s
curl -fLsS https://mrcoder.github.io/skills/$s/SKILL.md -o ~/.claude/skills/$s/SKILL.md
done
dest=~/.claude/skills/diagram
base=https://mrcoder.github.io/skills/diagram
mkdir -p "$dest/references"
for f in SKILL.md references/diagram-rules.md references/mermaid-syntax.md references/zenuml-syntax.md; do
curl -fLsS "$base/$f" -o "$dest/$f"
done
(
set -e
dest=~/.claude/skills
tmp=$(mktemp -d)
trap 'rm -rf "$tmp"' EXIT
base=https://mrcoder.github.io/downloads/search-conversation-history.zip
curl -fLsS "$base" -o "$tmp/search-conversation-history.zip"
curl -fLsS "$base.sha256" -o "$tmp/search-conversation-history.zip.sha256"
(cd "$tmp" && shasum -a 256 -c search-conversation-history.zip.sha256)
mkdir -p "$dest"
unzip -oq "$tmp/search-conversation-history.zip" -d "$dest"
python3 "$dest/search-conversation-history/scripts/history.py" index
)
dest=~/.claude/skills/unattended
base=https://mrcoder.github.io/skills/unattended
mkdir -p "$dest/scripts" "$dest/templates"
for f in SKILL.md READINESS.md LOOP.md scripts/run_guard.py templates/PLAN.md templates/REPORT.html templates/state.json; do
curl -fLsS "$base/$f" -o "$dest/$f"
done
mkdir -p ~/.claude/skills/overnight
curl -fLsS https://mrcoder.github.io/skills/overnight/SKILL.md \
-o ~/.claude/skills/overnight/SKILL.md
Cuts jargon and irrelevant detail, then leads with the conclusion and next steps.
It currently rewrites answers in plain Chinese. Use renhua as an alias.
/no-bs or $no-bs
/renhua or $renhua
"说人话"
Download ZIP ·
SHA-256 checksum.
The archive contains sibling no-bs and renhua folders;
unzip it into your skills root (for example ~/.claude/skills) so both
files install in place. Codex users can use ~/.codex/skills instead.
# no-bs is canonical; renhua is its backwards-compatible alias.
mkdir -p ~/.claude/skills/no-bs ~/.claude/skills/renhua
curl -fLsS https://mrcoder.github.io/skills/no-bs/SKILL.md \
-o ~/.claude/skills/no-bs/SKILL.md
curl -fLsS https://mrcoder.github.io/skills/renhua/SKILL.md \
-o ~/.claude/skills/renhua/SKILL.md
Reconstructs decisions across Codex, Claude Code, and Cursor when the session is
unknown, the question crosses sources, or an approach evolved over time. Use a
targeted rg search when you already know the file and one keyword.
The package includes the native history CLI (with optional MCP support),
a CLI launcher, and a Python fallback. Indexing and search run locally without an
API key. Setup requires Python 3.11+; Apple Silicon Macs use the bundled executable.
Other platforms build the included source with Rust/Cargo and a C compiler.
The search footer reports elapsed time (including any refresh) and cache-separated
uncached input, cached input, and output, with cache writes separately when nonzero.
Counters stop at the latest usage event before the final response; unavailable values
stay unavailable. Benchmark
mode is $search-conversation-history benchmark <question>
(Claude also accepts /search-conversation-history benchmark <question>).
"search conversation history"
"how did we handle this before?"
"find the earlier discussion about X"
Download ZIP ·
SHA-256 checksum ·
Install guide.
The command below installs the full package and creates the local index.
The skill uses the CLI directly: no MCP configuration or client restart is needed.
For Codex, change dest to ~/.codex/skills.
The Apple Silicon path has been verified; other platforms require a source build.
Generates sequence diagrams as ZenUML and other diagram types as Mermaid,
with optional image rendering. SVG diagrams — generated or improved — follow
a fidelity contract: preserve the business structure, route connectors with
deterministic geometry, and verify the rendered result instead of silently
redesigning it.
"draw a diagram"
"show me the flow"
"improve this SVG"
dest=~/.claude/skills/diagram
base=https://mrcoder.github.io/skills/diagram
mkdir -p "$dest/references"
for f in SKILL.md references/diagram-rules.md references/mermaid-syntax.md references/zenuml-syntax.md; do
curl -fLsS "$base/$f" -o "$dest/$f"
done
Turns a list into a sequence — re-verify the item, check it is still worth
doing, recommend the one action you judge correct, then act within the
existing authorization. A batch of twelve worktrees or open PRs stops being
twelve parallel guesses and becomes twelve decisions you can redirect mid-stream.
No option menu: you already chose to work the list, so the skill does not
hand that decision back.
Keeps useful work moving for a bounded time while you're away. It starts slow
CI, builds, and browser checks early, limits itself to two workstreams, guards
token allowance before every dispatch, and leaves a live evidence-backed HTML
report. Missing credentials or telemetry narrow the run; they do not waste it, and a
temporary lack of authorized work leaves the run idle rather than complete.
"work on this unattended"
"keep going while I'm AFK"
"work on this for two hours"
dest=~/.claude/skills/unattended
base=https://mrcoder.github.io/skills/unattended
mkdir -p "$dest/scripts" "$dest/templates"
for f in SKILL.md READINESS.md LOOP.md scripts/run_guard.py templates/PLAN.md templates/REPORT.html templates/state.json; do
curl -fLsS "$base/$f" -o "$dest/$f"
done
Extends unattended work into an eight-hour all-night profile. It checks that
credentials, browsers, runners, long waits, and the machine itself can survive
until morning, then applies the same bounded allowance and evidence rules and
writes a morning report.
"work on this overnight"
"run this all night"
"have this ready by morning"
dest=~/.claude/skills/unattended
base=https://mrcoder.github.io/skills/unattended
mkdir -p "$dest/scripts" "$dest/templates"
for f in SKILL.md READINESS.md LOOP.md scripts/run_guard.py templates/PLAN.md templates/REPORT.html templates/state.json; do
curl -fLsS "$base/$f" -o "$dest/$f"
done
mkdir -p ~/.claude/skills/overnight
curl -fLsS https://mrcoder.github.io/skills/overnight/SKILL.md \
-o ~/.claude/skills/overnight/SKILL.md
Surfaces what you don't know to ask before you start. Give it your experience
level and it greps the codebase's own history — commit messages, docs, past
incidents — for the landmines you can't see yet.
A live log of every place the plan met an edge case it didn't account for.
Picks the conservative option, writes down why, keeps building — so the
deviation is visible instead of buried in a diff.
Confirms the behavior actually works — drives a live browser or CLI against a
deployed site, not a local fixture. Writes the pass/fail plan before touching
anything, then observes a real signal for each check. Ephemeral by design: no new
spec file, no green test that proves nothing.
Requires a one-at-a-time, numbered quiz on your own change before merging,
unless the user explicitly skips it. Reading a diff isn't the same as
understanding the behavior it produces — a focused re-quiz is required only
when every answer is wrong.
Packages the prototype, the plan, and the deviation log into one self-contained
HTML page for the person who wasn't in the room — leads with the demo, answers
the objections a reviewer would already have.