bridge
Skill10 starsChanged 39 days agoMITView on GitHub
Capture a cross-project connection the moment it surfaces, such as a shared pattern, a person carrying context between projects, a story that lends another project credibility, a feedback loop. Use when one project feeds, reuses, reinforces another: 'connects to', 'feeds into', 'same pattern as'. Writes one YAML file per bridge to a bridges directory, with list, map and stats subcommands.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- ChainGPT-org/chaingpt-claude-skilltheir own version, first seen Nov 1, 2026
- tyler-berggren/tb-claude-kittheir own version, first seen Oct 7, 2026
- serdardb/context-bridgetheir own version, first seen Sep 18, 2026
- msanchezdev/agent-bridgetheir own version, first seen Jun 17, 2026
- EthanSK/agent-bridgetheir own version, first seen Apr 12, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- msanchezdev/agent-bridge★ 20same name
- EthanSK/agent-bridge★ 11same name
- ChainGPT-org/chaingpt-claude-skill★ 7same name
- serdardb/context-bridge★ 4same name
- tyler-berggren/tb-claude-kit★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository81 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/development/biome-complete/AGENTS.mdAGENTS.md
- skills/development/bun-development/AGENTS.mdAGENTS.md
- skills/development/commanderjs/AGENTS.mdAGENTS.md
- skills/documentation/markdown-authoring/AGENTS.mdAGENTS.md
- skills/package-mgmt/mise-complete/AGENTS.mdAGENTS.md
- skills/testing/bdd-testing/AGENTS.mdAGENTS.md
- agents-mdSkill
- cache-auditSkill
- context-radar-auditSkill
- create-contextSkill
- guided-interviewSkill
- handover-document-creatorSkill
- load-contextSkill
- pick-modelSkill
- pinSkill
- professional-honestySkill
- rules-managementSkill
- save-contextSkill
- session-reflectionSkill
- socratic-methodSkill
- vault-captureSkill
- vault-consolidateSkill
- vault-fetchSkill
- vault-searchSkill
- bird-fortune-political-satireSkill
- brooker-esque-media-satireSkill
- clarke-dawe-esqueSkill
- comedy-style-skill-generatorSkill
- cunk-esque-mockumentarySkill
- gervais-esque-cringe-satireSkill
- monty-python-esqueSkill
- pryor-esque-confessional-standupSkill
- rock-esque-observational-standupSkill
- biome-completeSkill
- bun-developmentSkill
- commanderjsSkill
- conventional-commitsSkill
- humanizerSkill
- journal-entry-importSkill
- markdown-authoringSkill
- mermaid-diagramsSkill
- plain-englishSkill
- professional-communicationSkill
- sop-structureSkill
- logql-generatorSkill
- mise-completeSkill
- context-indexSkill
- create-context-fileSkill
- follow-upSkill
- goal-trackerSkill
- nasa-pm-lessonsSkill
- plan-createSkill
- plan-executeSkill
- plan-reviewSkill
- risk-registerSkill
- tech-debtSkill
- tech-evaluationSkill
- blast-radiusSkill
- challengeSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. 0 are common, 14 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
14
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Write to the bridges directory only.
- Distinctive: line 23
Use it when the user says "this connects to" or "same pattern as" another project.
- Distinctive: line 24
Use it when a person who works across two projects carries context between them.
- Distinctive: line 25
Use it when a session produces a story or proof point that strengthens another project.
- Distinctive: line 30
Avoid capturing administrative links (shared calendar, same channel) that move no knowledge.
- Distinctive: line 31
Avoid capturing when both names point at one project.
- Very specific: line 32
Stop and wait when the user is mid-decision, until a natural pause or an explicit /bridge.
- Distinctive: line 33
Check for an existing bridge first, and never recapture a link that is already stored.
- Distinctive: line 34
Avoid capturing during a weekly review, because bridges are for in-the-moment capture.
- Very specific: line 38
Run /bridge <src> → <tgt>: <desc> to capture, adding [type] after the target to force an archetype.
- Very specific: line 42
Read the project config at $PRAXIS_DIR.
- Distinctive: line 48
Check for a duplicate, then write the file following storage and schema.
- Very specific: line 55
When three or more bridges this week share one project pair, append 📊 {N} bridges this week involving {pair}.
- Distinctive: line 66
NEVER reformulate the user's description.
- Distinctive: line 67
NEVER comment on the bridge content.
- Distinctive: line 68
NEVER write to GTD files or project artifacts.
- Distinctive: line 69
NEVER invent an alias that is not in config.
- Distinctive: line 70
NEVER count files to get the sequence number, because after a deletion the count collides and overwrites a capture.
- Very specific: line 71
NEVER guess a rare archetype (local, mirror, complexity) on one keyword.
- Very specific: line 72
NEVER hardcode one-way and potential.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Bridge: Cross-Project Connection Capture
Capture a bridge while you are still in context. Keep it in the bridges directory, never in project artifacts.
Principles
- Capture fast, then step aside: answer in one line and resume the conversation that produced the link.
- Store the user's words, not yours, because a paraphrase erases the mental model that triggered the link.
- Choose an honest default over a confident guess; a wrong rare archetype hides in the stats, while a visible
knowledgedefault gets corrected. - Write to the bridges directory only.
When to Use
- Use it when the user says "this connects to" or "same pattern as" another project.
- Use it when a person who works across two projects carries context between them.
- Use it when a session produces a story or proof point that strengthens another project.
- Capture a stated link even without
/bridge, provided both projects resolve from config.
When Not to Use
- Avoid capturing administrative links (shared calendar, same channel) that move no knowledge.
- Avoid capturing when both names point at one project; fix the alias in config instead.
- Stop and wait when the user is mid-decision, until a natural pause or an explicit
/bridge. - Check for an existing bridge first, and never recapture a link that is already stored.
- Avoid capturing during a weekly review, because bridges are for in-the-moment capture.
Commands
Run /bridge <src> → <tgt>: <desc> to capture, adding [type] after the target to force an archetype. Read list, map and stats output, then run /bridge list [project], /bridge map or /bridge stats to read bridges back.
Capture Procedure
- Read the project config at
$PRAXIS_DIR. It holds aliases, names, tiers, flywheel roles and stakeholders withalso_in. If it is missing, stop with⚠️ No project config found. Create it with your project definitions. - Split the input on
→or↔for the source, then on:for the target, any[type]and the description. - Resolve both aliases against config keys, case-insensitively, then fuzzy-match against
name. If either fails, write nothing. Warn and suggest adding the project to config. - Pick the archetype. Use
[type]when given, otherwise apply archetype detection. When the signal is weak, useknowledgeand say so. - Set the direction. Use
bidirectionalfor↔, "bidirectional" or "both ways", otherwiseone-way. - Set the strength. Check hedges first ("maybe", "in theory" give
theoretical), then present tense ("already", "carries" giveactive), then "not yet", "should", "if it works" forpotential. Default topotential. - Check for a duplicate, then write the file following storage and schema.
- Answer with one line, then resume the prior conversation. Use
↔for bidirectional bridges and add, defaultedin the brackets after a defaulted archetype:
🔗 Bridge #N: {emoji} {source} → {target} ({archetype}) — {short desc}When three or more bridges this week share one project pair, append 📊 {N} bridges this week involving {pair}. Update strategic bridges during review.
Take the highest number used today, add one, then confirm the file parses:
last="$(ls "$dir" | sed -n "s/^$(date +%F)-\([0-9]*\)-.*/\1/p" | sort -n | tail -1)"; seq=$(( ${last:-0} + 1 ))
yq '.' ./thinking/bridges/"$file" > /dev/nullAnti-Patterns
- NEVER reformulate the user's description. WHY: a paraphrase adds your interpretation and erases the original mental model.
- NEVER comment on the bridge content. Keep the response to one line, because commentary derails the conversation.
- NEVER write to GTD files or project artifacts; mixing captures into task lists pollutes both.
- NEVER invent an alias that is not in config; invented aliases break list, map and stats.
- NEVER count files to get the sequence number, because after a deletion the count collides and overwrites a capture. Always use the highest number plus one.
- NEVER guess a rare archetype (
local,mirror,complexity) on one keyword; the pitfall is a mislabel that skews the stats unseen. - NEVER hardcode
one-wayandpotential; run steps 5 and 6 so the stats do not repeat a wrong relationship.
# BAD: "Matthieu carries context both ways" stored with the defaults
direction: one-way
strength: potential
# GOOD: "both ways" is bidirectional, "carries" is present tense
direction: bidirectional
strength: activeReferences
- Archetype Detection: the 10 archetypes and the signals for picking one
- Storage and Schema: filename, sequence number, YAML schema, write guards, duplicate check
- List, Map and Stats: output formats for the read-only subcommands
- Worked Examples: three captures showing how the signals combine
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

